Search

For FMCG (fast-moving consumer goods) the store is an excellent and effective place not only to sell products but also to expose shoppers to a brand. This is a key part of the retail marketing strategy known as shopper marketing. Shopper marketing is not only a way for suppliers to attract customers to their brands but also a source of revenue for retailers, who can sell prime advertising real estate and shelf space inside the store. However, shopper marketing is not just about investment. It is also about a shared focus on the shopper—not the consumer and not the store, but the shopper who is present in the store and throughout the entire purchasing journey.Despite the changes in the grocery retail industry in recent years, some things remain the same. Brand suppliers to the grocery retail industry need to develop mutually beneficial shopper marketing collaborations with retailers. Such collaborations can be the foundation not only for successful sales but also for a competitive store if there is strategic alignment between the retailer and the brand suppliers.

Ptychography has evolved as an important method for nanoscale X-ray imaging with synchrotron radiation. Recently, it has been proposed to work with multiple beams in parallel. The main advantage of so-called multi-beam ptychography is that larger areas can be imaged much faster than with a conventional single beam scan. We introduce adaptive multi-beam ptychography performed with two Fresnel zone plates, placed one behind the other. In contrast to previous demonstrations of multi-beam ptychography, our optical scheme allows for adapting the spatial beam separation to the needs of the sample under investigation, relaxes thickness requirements on zone plates and is straightforward to implement. Moreover, it is simple to switch between single and multi-beam illumination during the same experiment. This opens the possibility of combining large and fast overview scans with detailed imaging of certain regions of interests., QC 20240704

Inpatient mental healthcare settings should offer safe environments for patients to heal and recover and for staff to provide high-quality treatment and care. However, aggressive patient behaviour, unengaged staff approaches, and the use of restrictive practices are frequently reported. The Safewards model includes ten interventions that aim to prevent conflict and containment. The model has shown promising results but at the same time often presents challenges to successful implementation strategies. The aim of this study was to review qualitative knowledge on staff experiences of barriers and enablers to the implementation of Safewards, from the perspective of implementation science and the i-PARIHS framework. A search of the Web of Science, ASSIA, Cochrane Library, SCOPUS, Medline, Embase, PsycINFO, and CINAHL databases resulted in 10 articles. A deductive framework analysis approach was used to identify barriers and enablers and the alignment to the i-PARIHS. Data most represented by the i-PARIHS were related to the following: local-level formal and informal leadership support, innovation degree of fit with existing practice and values, and recipients' values and beliefs. This indicates that if a ward or organization wants to implement Safewards and direct limited resources to only a few implementation determinants, these three may be worth considering. Data representing levels of external health system and organizational contexts were rare. In contrast, data relating to local (ward)-level contexts was highly represented which may reflect Safewards's focus on quality improvement strategies on a local rather than organizational level. © 2023 The Authors. International Journal of Mental Health Nursing published by John Wiley & Sons Australia, Ltd., Open access funding was provided by the Karolinska Institutet., Safewards Sverige

Inpatient mental healthcare settings should offer safe environments for patients to heal and recover and for staff to provide high-quality treatment and care. However, aggressive patient behaviour, unengaged staff approaches, and the use of restrictive practices are frequently reported. The Safewards model includes ten interventions that aim to prevent conflict and containment. The model has shown promising results but at the same time often presents challenges to successful implementation strategies. The aim of this study was to review qualitative knowledge on staff experiences of barriers and enablers to the implementation of Safewards, from the perspective of implementation science and the i-PARIHS framework. A search of the Web of Science, ASSIA, Cochrane Library, SCOPUS, Medline, Embase, PsycINFO, and CINAHL databases resulted in 10 articles. A deductive framework analysis approach was used to identify barriers and enablers and the alignment to the i-PARIHS. Data most represented by the i-PARIHS were related to the following: local-level formal and informal leadership support, innovation degree of fit with existing practice and values, and recipients' values and beliefs. This indicates that if a ward or organization wants to implement Safewards and direct limited resources to only a few implementation determinants, these three may be worth considering. Data representing levels of external health system and organizational contexts were rare. In contrast, data relating to local (ward)-level contexts was highly represented which may reflect Safewards's focus on quality improvement strategies on a local rather than organizational level. © 2023 The Authors. International Journal of Mental Health Nursing published by John Wiley & Sons Australia, Ltd., Open access funding was provided by the Karolinska Institutet., Safewards Sverige

Inpatient mental healthcare settings should offer safe environments for patients to heal and recover and for staff to provide high-quality treatment and care. However, aggressive patient behaviour, unengaged staff approaches, and the use of restrictive practices are frequently reported. The Safewards model includes ten interventions that aim to prevent conflict and containment. The model has shown promising results but at the same time often presents challenges to successful implementation strategies. The aim of this study was to review qualitative knowledge on staff experiences of barriers and enablers to the implementation of Safewards, from the perspective of implementation science and the i-PARIHS framework. A search of the Web of Science, ASSIA, Cochrane Library, SCOPUS, Medline, Embase, PsycINFO, and CINAHL databases resulted in 10 articles. A deductive framework analysis approach was used to identify barriers and enablers and the alignment to the i-PARIHS. Data most represented by the i-PARIHS were related to the following: local-level formal and informal leadership support, innovation degree of fit with existing practice and values, and recipients' values and beliefs. This indicates that if a ward or organization wants to implement Safewards and direct limited resources to only a few implementation determinants, these three may be worth considering. Data representing levels of external health system and organizational contexts were rare. In contrast, data relating to local (ward)-level contexts was highly represented which may reflect Safewards's focus on quality improvement strategies on a local rather than organizational level. © 2023 The Authors. International Journal of Mental Health Nursing published by John Wiley & Sons Australia, Ltd., Open access funding was provided by the Karolinska Institutet., Safewards Sverige

While local explanations for AI models can offer insights into individual predictions, such as feature importance, they are plagued by issues like instability. The unreliability of feature weights, often skewed due to poorly calibrated ML models, deepens these challenges. Moreover, the critical aspect of feature importance uncertainty remains mostly unaddressed in Explainable AI (XAI). The novel feature importance explanation method presented in this paper, called Calibrated Explanations (CE), is designed to tackle these issues head-on. Built on the foundation of Venn-Abers, CE not only calibrates the underlying model but also delivers reliable feature importance explanations with an exact definition of the feature weights. CE goes beyond conventional solutions by addressing output uncertainty. It accomplishes this by providing uncertainty quantification for both feature weights and the model’s probability estimates. Additionally, CE is model-agnostic, featuring easily comprehensible conditional rules and the ability to generate counterfactual explanations with embedded uncertainty quantification. Results from an evaluation with 25 benchmark datasets underscore the efficacy of CE, making it stand as a fast, reliable, stable, and robust solution., Included in doctoral thesis in manuscript form.

Inpatient mental healthcare settings should offer safe environments for patients to heal and recover and for staff to provide high-quality treatment and care. However, aggressive patient behaviour, unengaged staff approaches, and the use of restrictive practices are frequently reported. The Safewards model includes ten interventions that aim to prevent conflict and containment. The model has shown promising results but at the same time often presents challenges to successful implementation strategies. The aim of this study was to review qualitative knowledge on staff experiences of barriers and enablers to the implementation of Safewards, from the perspective of implementation science and the i-PARIHS framework. A search of the Web of Science, ASSIA, Cochrane Library, SCOPUS, Medline, Embase, PsycINFO, and CINAHL databases resulted in 10 articles. A deductive framework analysis approach was used to identify barriers and enablers and the alignment to the i-PARIHS. Data most represented by the i-PARIHS were related to the following: local-level formal and informal leadership support, innovation degree of fit with existing practice and values, and recipients' values and beliefs. This indicates that if a ward or organization wants to implement Safewards and direct limited resources to only a few implementation determinants, these three may be worth considering. Data representing levels of external health system and organizational contexts were rare. In contrast, data relating to local (ward)-level contexts was highly represented which may reflect Safewards's focus on quality improvement strategies on a local rather than organizational level. © 2023 The Authors. International Journal of Mental Health Nursing published by John Wiley & Sons Australia, Ltd., Open access funding was provided by the Karolinska Institutet., Safewards Sverige

Inpatient mental healthcare settings should offer safe environments for patients to heal and recover and for staff to provide high-quality treatment and care. However, aggressive patient behaviour, unengaged staff approaches, and the use of restrictive practices are frequently reported. The Safewards model includes ten interventions that aim to prevent conflict and containment. The model has shown promising results but at the same time often presents challenges to successful implementation strategies. The aim of this study was to review qualitative knowledge on staff experiences of barriers and enablers to the implementation of Safewards, from the perspective of implementation science and the i-PARIHS framework. A search of the Web of Science, ASSIA, Cochrane Library, SCOPUS, Medline, Embase, PsycINFO, and CINAHL databases resulted in 10 articles. A deductive framework analysis approach was used to identify barriers and enablers and the alignment to the i-PARIHS. Data most represented by the i-PARIHS were related to the following: local-level formal and informal leadership support, innovation degree of fit with existing practice and values, and recipients' values and beliefs. This indicates that if a ward or organization wants to implement Safewards and direct limited resources to only a few implementation determinants, these three may be worth considering. Data representing levels of external health system and organizational contexts were rare. In contrast, data relating to local (ward)-level contexts was highly represented which may reflect Safewards's focus on quality improvement strategies on a local rather than organizational level.

Product returns are not only costly for e-tailers, but the unnecessary transports also impact the environment. Consequently, online retailers have started to formulate policies to reduce the number of returns. Determining when and how to act is, however, a delicate matter, since a too harsh approach may lead to not only the order being cancelled, but also the customer leaving the business. Being able to accurately predict which orders that will lead to a return would be a strong tool, guiding which actions to be taken. This paper addresses the problem of data-driven product return prediction, by conducting a case study using a large real-world data set. The main results are that well-calibrated probabilistic predictors are essential for providing predictions with high precision and reasonable recall. This implies that utilizing calibrated models to predict some instances, while rejecting to predict others can be recommended. In practice, this would make it possible for a decision-maker to only act upon a subset of all predicted returns, where the risk of a return is very high., ©2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.This research is a part of the industrial graduate research school in digital retailing (INSiDR) at the University of Borås, funded by The Swedish Knowledge Foundation, grants nr. 20160035, 20170215., INSiDR

Being able to understand the logic behind predictions or recommendations on the instance level is at the heart of trustworthy machine learning models. Inherently interpretable models make this possible by allowing inspection and analysis of the model itself, thus exhibiting the logic behind each prediction, while providing an opportunity to gain insights about the underlying domain. Another important criterion for trustworthiness is the model’s ability to somehow communicate a measure of confidence in every specific prediction or recommendation. Indeed, the overall goal of this paper is to produce highly informative models that combine interpretability and algorithmic confidence. For this purpose, we introduce conformal predictive distribution trees, which is a novel form of regression trees where each leaf contains a conformal predictive distribution. Using this representation language, the proposed approach allows very versatile analyses of individual leaves in the regression trees. Specifically, depending on the chosen level of detail, the leaves, in addition to the normal point predictions, can provide either cumulative distributions or prediction intervals that are guaranteed to be well-calibrated. In the empirical evaluation, the suggested conformal predictive distribution trees are compared to the well-established conformal regressors, thus demonstrating the benefits of the enhanced representation., QC 20240807

Low nutrient availability often limits productivity in northern forests. In a nutrient optimisation trial, we investigated the effects of fertilisation and irrigation on soil moisture, leaf area index (LAI) as well as height and radial growth in 25-year-old stands of pedunculate and sessile oak (Quercus robur L., Q. petraea (Matt.) Liebl.) growing on abandoned farmland in southwestern Sweden. Control (C), fertilisation (F), irrigation (I), and irrigation +fertilisation (IF) treatments were arranged in a randomized complete block design. End of growing season analysis of foliar nutrients guided the quantitative composition of next year’s fertiliser mix. Volumetric soil moisture (VWC) was significantly higher in the I and IF treatments compared to the C and F treated stands of both oak species. We did not observe a fertiliser-related reduction in VWC (except for 2015, when VWC in F- treated Q. robur stands was significantly lower than the control by about 18 %). This is in line with the unaffected LAI estimates (5.3–5.9) suggesting no stimulation of leaf production that could drive increases in transpiration with subsequent soil moisture depletion. There was no treatment ×year interaction for any of the growth-related variables. Treatments had no significant effects on basal area growth, which increased annually by 1.72 and 1.54 m2 ha-1 on average for Q. petraea and Q. robur, respectively. Pre-treatment height differences in Q. petraea stands (7–12 % taller trees in the C and IF plots) persisted throughout the study resulting in significant effects, while no significant differences in height occurred in Q. robur. Periodic annual volume increment varied more strongly following drier periods but there were no significant differences among treatments. Our findings indicate that fertilisation causes no or only minor increases in oak water use, suggesting that nutrient addition in oak stands within this precipitation regime does not require simultaneous irrigation. Most im

Trees constitute promising renewable feedstocks for biorefinery using biochemical conversion, but their recalcitrance restricts their attractiveness for the industry. To obtain trees with reduced recalcitrance, large-scale genetic engineering experiments were performed in hybrid aspen blindly targeting genes expressed during wood formation and 32 lines representing seven constructs were selected for characterization in the field. Here we report phenotypes of five-year old trees considering 49 traits related to growth and wood properties. The best performing construct considering growth and glucose yield in saccharification with acid pretreatment had suppressed expression of the gene encoding an uncharacterized 2-oxoglutarate-dependent dioxygenase (2OGD). It showed minor changes in wood chemistry but increased nanoporosity and glucose conversion. Suppressed levels of SUCROSE SYNTHASE, (SuSy), CINNAMATE 4-HYDROXYLASE (C4H) and increased levels of GTPase activating protein for ADP-ribosylation factor ZAC led to significant growth reductions and anatomical abnormalities. However, C4H and SuSy constructs greatly improved glucose yields in saccharification without and with pretreatment, respectively. Traits associated with high glucose yields were different for saccharification with and without pretreatment. While carbohydrates, phenolics and tension wood contents positively impacted the yields without pretreatment and growth, lignin content and S/G ratio were negative factors, the yields with pretreatment positively correlated with S lignin and negatively with carbohydrate contents. The genotypes with high glucose yields had increased nanoporosity and mGlcA/Xyl ratio, and some had shorter polymers extractable with subcritical water compared to wild-type. The pilot-scale industrial-like pretreatment of best-performing 2OGD construct confirmed its superior sugar yields, supporting our strategy.

Trees constitute promising renewable feedstocks for biorefinery using biochemical conversion, but their recalcitrance restricts their attractiveness for the industry. To obtain trees with reduced recalcitrance, large-scale genetic engineering experiments were performed in hybrid aspen blindly targeting genes expressed during wood formation and 32 lines representing seven constructs were selected for characterization in the field. Here we report phenotypes of five-year old trees considering 49 traits related to growth and wood properties. The best performing construct considering growth and glucose yield in saccharification with acid pretreatment had suppressed expression of the gene encoding an uncharacterized 2-oxoglutarate-dependent dioxygenase (2OGD). It showed minor changes in wood chemistry but increased nanoporosity and glucose conversion. Suppressed levels of SUCROSE SYNTHASE, (SuSy), CINNAMATE 4-HYDROXYLASE (C4H) and increased levels of GTPase activating protein for ADP-ribosylation factor ZAC led to significant growth reductions and anatomical abnormalities. However, C4H and SuSy constructs greatly improved glucose yields in saccharification without and with pretreatment, respectively. Traits associated with high glucose yields were different for saccharification with and without pretreatment. While carbohydrates, phenolics and tension wood contents positively impacted the yields without pretreatment and growth, lignin content and S/G ratio were negative factors, the yields with pretreatment positively correlated with S lignin and negatively with carbohydrate contents. The genotypes with high glucose yields had increased nanoporosity and mGlcA/Xyl ratio, and some had shorter polymers extractable with subcritical water compared to wild-type. The pilot-scale industrial-like pretreatment of best-performing 2OGD construct confirmed its superior sugar yields, supporting our strategy.

Low nutrient availability often limits productivity in northern forests. In a nutrient optimisation trial, we investigated the effects of fertilisation and irrigation on soil moisture, leaf area index (LAI) as well as height and radial growth in 25-year-old stands of pedunculate and sessile oak (Quercus robur L., Q. petraea (Matt.) Liebl.) growing on abandoned farmland in southwestern Sweden. Control (C), fertilisation (F), irrigation (I), and irrigation +fertilisation (IF) treatments were arranged in a randomized complete block design. End of growing season analysis of foliar nutrients guided the quantitative composition of next year’s fertiliser mix. Volumetric soil moisture (VWC) was significantly higher in the I and IF treatments compared to the C and F treated stands of both oak species. We did not observe a fertiliser-related reduction in VWC (except for 2015, when VWC in F- treated Q. robur stands was significantly lower than the control by about 18 %). This is in line with the unaffected LAI estimates (5.3–5.9) suggesting no stimulation of leaf production that could drive increases in transpiration with subsequent soil moisture depletion. There was no treatment ×year interaction for any of the growth-related variables. Treatments had no significant effects on basal area growth, which increased annually by 1.72 and 1.54 m2 ha-1 on average for Q. petraea and Q. robur, respectively. Pre-treatment height differences in Q. petraea stands (7–12 % taller trees in the C and IF plots) persisted throughout the study resulting in significant effects, while no significant differences in height occurred in Q. robur. Periodic annual volume increment varied more strongly following drier periods but there were no significant differences among treatments. Our findings indicate that fertilisation causes no or only minor increases in oak water use, suggesting that nutrient addition in oak stands within this precipitation regime does not require simultaneous irrigation. Most im

Trees constitute promising renewable feedstocks for biorefinery using biochemical conversion, but their recalcitrance restricts their attractiveness for the industry. To obtain trees with reduced recalcitrance, large-scale genetic engineering experiments were performed in hybrid aspen blindly targeting genes expressed during wood formation and 32 lines representing seven constructs were selected for characterization in the field. Here we report phenotypes of five-year old trees considering 49 traits related to growth and wood properties. The best performing construct considering growth and glucose yield in saccharification with acid pretreatment had suppressed expression of the gene encoding an uncharacterized 2-oxoglutarate-dependent dioxygenase (2OGD). It showed minor changes in wood chemistry but increased nanoporosity and glucose conversion. Suppressed levels of SUCROSE SYNTHASE, (SuSy), CINNAMATE 4-HYDROXYLASE (C4H) and increased levels of GTPase activating protein for ADP-ribosylation factor ZAC led to significant growth reductions and anatomical abnormalities. However, C4H and SuSy constructs greatly improved glucose yields in saccharification without and with pretreatment, respectively. Traits associated with high glucose yields were different for saccharification with and without pretreatment. While carbohydrates, phenolics and tension wood contents positively impacted the yields without pretreatment and growth, lignin content and S/G ratio were negative factors, the yields with pretreatment positively correlated with S lignin and negatively with carbohydrate contents. The genotypes with high glucose yields had increased nanoporosity and mGlcA/Xyl ratio, and some had shorter polymers extractable with subcritical water compared to wild-type. The pilot-scale industrial-like pretreatment of best-performing 2OGD construct confirmed its superior sugar yields, supporting our strategy.

Xylan that comprises roughly 25% of hardwood biomass is undesirable in biorefinery applications involving saccharification and fermentation. Efforts to reduce xylan levels have therefore been made in many species, usually resulting in improved saccharification. However, such modified plants have not yet been tested under field conditions. Here we evaluate the field performance of transgenic hybrid aspen lines with reduced xylan levels and assess their usefulness as short-rotation feedstocks for biorefineries. Three types of transgenic lines were tested in four-year field tests with RNAi constructs targeting either Populus GT43 clades B and C (GT43BC) corresponding to Arabidopsis clades IRX9 and IRX14, respectively, involved in xylan backbone biosynthesis, GATL1.1 corresponding to AtGALT1 involved in xylan reducing end sequence biosynthesis, or ASPR1 encoding an atypical aspartate protease. Their productivity, wood quality traits, and saccharification efficiency were analyzed. The only lines differing significantly from the wild type with respect to growth and biotic stress resistance were the ASPR1 lines, whose stems were roughly 10% shorter and narrower and leaves showed increased arthropod damage. GT43BC lines exhibited no growth advantage in the field despite their superior growth in greenhouse experiments. Wood from the ASPR1 and GT43BC lines had slightly reduced density due to thinner cell walls and, in the case of ASPR1, larger cell diameters. The xylan was less extractable by alkali but more hydrolysable by acid, had increased glucuronosylation, and its content was reduced in all three types of transgenic lines. The hemicellulose size distribution in the GALT1.1 and ASPR1 lines was skewed towards higher molecular mass compared to the wild type. These results provide experimental evidence that GATL1.1 functions in xylan biosynthesis and suggest that ASPR1 may regulate this process. In saccharification without pretreatment, lines of all three constructs provide

Xylan that comprises roughly 25% of hardwood biomass is undesirable in biorefinery applications involving saccharification and fermentation. Efforts to reduce xylan levels have therefore been made in many species, usually resulting in improved saccharification. However, such modified plants have not yet been tested under field conditions. Here we evaluate the field performance of transgenic hybrid aspen lines with reduced xylan levels and assess their usefulness as short-rotation feedstocks for biorefineries. Three types of transgenic lines were tested in four-year field tests with RNAi constructs targeting either Populus GT43 clades B and C (GT43BC) corresponding to Arabidopsis clades IRX9 and IRX14, respectively, involved in xylan backbone biosynthesis, GATL1.1 corresponding to AtGALT1 involved in xylan reducing end sequence biosynthesis, or ASPR1 encoding an atypical aspartate protease. Their productivity, wood quality traits, and saccharification efficiency were analyzed. The only lines differing significantly from the wild type with respect to growth and biotic stress resistance were the ASPR1 lines, whose stems were roughly 10% shorter and narrower and leaves showed increased arthropod damage. GT43BC lines exhibited no growth advantage in the field despite their superior growth in greenhouse experiments. Wood from the ASPR1 and GT43BC lines had slightly reduced density due to thinner cell walls and, in the case of ASPR1, larger cell diameters. The xylan was less extractable by alkali but more hydrolysable by acid, had increased glucuronosylation, and its content was reduced in all three types of transgenic lines. The hemicellulose size distribution in the GALT1.1 and ASPR1 lines was skewed towards higher molecular mass compared to the wild type. These results provide experimental evidence that GATL1.1 functions in xylan biosynthesis and suggest that ASPR1 may regulate this process. In saccharification without pretreatment, lines of all three constructs provide, QC 20230818

Trees constitute promising renewable feedstocks for biorefinery using biochemical conversion, but their recalcitrance restricts their attractiveness for the industry. To obtain trees with reduced recalcitrance, large-scale genetic engineering experiments were performed in hybrid aspen blindly targeting genes expressed during wood formation and 32 lines representing seven constructs were selected for characterization in the field. Here we report phenotypes of five-year old trees considering 49 traits related to growth and wood properties. The best performing construct considering growth and glucose yield in saccharification with acid pretreatment had suppressed expression of the gene encoding an uncharacterized 2-oxoglutarate-dependent dioxygenase (2OGD). It showed minor changes in wood chemistry but increased nanoporosity and glucose conversion. Suppressed levels of SUCROSE SYNTHASE, (SuSy), CINNAMATE 4-HYDROXYLASE (C4H) and increased levels of GTPase activating protein for ADP-ribosylation factor ZAC led to significant growth reductions and anatomical abnormalities. However, C4H and SuSy constructs greatly improved glucose yields in saccharification without and with pretreatment, respectively. Traits associated with high glucose yields were different for saccharification with and without pretreatment. While carbohydrates, phenolics and tension wood contents positively impacted the yields without pretreatment and growth, lignin content and S/G ratio were negative factors, the yields with pretreatment positively correlated with S lignin and negatively with carbohydrate contents. The genotypes with high glucose yields had increased nanoporosity and mGlcA/Xyl ratio, and some had shorter polymers extractable with subcritical water compared to wild-type. The pilot-scale industrial-like pretreatment of best-performing 2OGD construct confirmed its superior sugar yields, supporting our strategy., QC 20230627

Xylan that comprises roughly 25% of hardwood biomass is undesirable in biorefinery applications involving saccharification and fermentation. Efforts to reduce xylan levels have therefore been made in many species, usually resulting in improved saccharification. However, such modified plants have not yet been tested under field conditions. Here we evaluate the field performance of transgenic hybrid aspen lines with reduced xylan levels and assess their usefulness as short-rotation feedstocks for biorefineries. Three types of transgenic lines were tested in four-year field tests with RNAi constructs targeting either Populus GT43 clades B and C (GT43BC) corresponding to Arabidopsis clades IRX9 and IRX14, respectively, involved in xylan backbone biosynthesis, GATL1.1 corresponding to AtGALT1 involved in xylan reducing end sequence biosynthesis, or ASPR1 encoding an atypical aspartate protease. Their productivity, wood quality traits, and saccharification efficiency were analyzed. The only lines differing significantly from the wild type with respect to growth and biotic stress resistance were the ASPR1 lines, whose stems were roughly 10% shorter and narrower and leaves showed increased arthropod damage. GT43BC lines exhibited no growth advantage in the field despite their superior growth in greenhouse experiments. Wood from the ASPR1 and GT43BC lines had slightly reduced density due to thinner cell walls and, in the case of ASPR1, larger cell diameters. The xylan was less extractable by alkali but more hydrolysable by acid, had increased glucuronosylation, and its content was reduced in all three types of transgenic lines. The hemicellulose size distribution in the GALT1.1 and ASPR1 lines was skewed towards higher molecular mass compared to the wild type. These results provide experimental evidence that GATL1.1 functions in xylan biosynthesis and suggest that ASPR1 may regulate this process. In saccharification without pretreatment, lines of all three constructs provide

Xylan that comprises roughly 25% of hardwood biomass is undesirable in biorefinery applications involving saccharification and fermentation. Efforts to reduce xylan levels have therefore been made in many species, usually resulting in improved saccharification. However, such modified plants have not yet been tested under field conditions. Here we evaluate the field performance of transgenic hybrid aspen lines with reduced xylan levels and assess their usefulness as short-rotation feedstocks for biorefineries. Three types of transgenic lines were tested in four-year field tests with RNAi constructs targeting either Populus GT43 clades B and C (GT43BC) corresponding to Arabidopsis clades IRX9 and IRX14, respectively, involved in xylan backbone biosynthesis, GATL1.1 corresponding to AtGALT1 involved in xylan reducing end sequence biosynthesis, or ASPR1 encoding an atypical aspartate protease. Their productivity, wood quality traits, and saccharification efficiency were analyzed. The only lines differing significantly from the wild type with respect to growth and biotic stress resistance were the ASPR1 lines, whose stems were roughly 10% shorter and narrower and leaves showed increased arthropod damage. GT43BC lines exhibited no growth advantage in the field despite their superior growth in greenhouse experiments. Wood from the ASPR1 and GT43BC lines had slightly reduced density due to thinner cell walls and, in the case of ASPR1, larger cell diameters. The xylan was less extractable by alkali but more hydrolysable by acid, had increased glucuronosylation, and its content was reduced in all three types of transgenic lines. The hemicellulose size distribution in the GALT1.1 and ASPR1 lines was skewed towards higher molecular mass compared to the wild type. These results provide experimental evidence that GATL1.1 functions in xylan biosynthesis and suggest that ASPR1 may regulate this process. In saccharification without pretreatment, lines of all three constructs provide

Low nutrient availability often limits productivity in northern forests. In a nutrient optimisation trial, we investigated the effects of fertilisation and irrigation on soil moisture, leaf area index (LAI) as well as height and radial growth in 25-year-old stands of pedunculate and sessile oak (Quercus robur L., Q. petraea (Matt.) Liebl.) growing on abandoned farmland in southwestern Sweden. Control (C), fertilisation (F), irrigation (I), and irrigation +fertilisation (IF) treatments were arranged in a randomized complete block design. End of growing season analysis of foliar nutrients guided the quantitative composition of next year’s fertiliser mix. Volumetric soil moisture (VWC) was significantly higher in the I and IF treatments compared to the C and F treated stands of both oak species. We did not observe a fertiliser-related reduction in VWC (except for 2015, when VWC in F- treated Q. robur stands was significantly lower than the control by about 18 %). This is in line with the unaffected LAI estimates (5.3–5.9) suggesting no stimulation of leaf production that could drive increases in transpiration with subsequent soil moisture depletion. There was no treatment ×year interaction for any of the growth-related variables. Treatments had no significant effects on basal area growth, which increased annually by 1.72 and 1.54 m2 ha-1 on average for Q. petraea and Q. robur, respectively. Pre-treatment height differences in Q. petraea stands (7–12 % taller trees in the C and IF plots) persisted throughout the study resulting in significant effects, while no significant differences in height occurred in Q. robur. Periodic annual volume increment varied more strongly following drier periods but there were no significant differences among treatments. Our findings indicate that fertilisation causes no or only minor increases in oak water use, suggesting that nutrient addition in oak stands within this precipitation regime does not require simultaneous irrigation. Most im

Inpatient mental healthcare settings should offer safe environments for patients to heal and recover and for staff to provide high-quality treatment and care. However, aggressive patient behaviour, unengaged staff approaches, and the use of restrictive practices are frequently reported. The Safewards model includes ten interventions that aim to prevent conflict and containment. The model has shown promising results but at the same time often presents challenges to successful implementation strategies. The aim of this study was to review qualitative knowledge on staff experiences of barriers and enablers to the implementation of Safewards, from the perspective of implementation science and the i-PARIHS framework. A search of the Web of Science, ASSIA, Cochrane Library, SCOPUS, Medline, Embase, PsycINFO, and CINAHL databases resulted in 10 articles. A deductive framework analysis approach was used to identify barriers and enablers and the alignment to the i-PARIHS. Data most represented by the i-PARIHS were related to the following: local-level formal and informal leadership support, innovation degree of fit with existing practice and values, and recipients' values and beliefs. This indicates that if a ward or organization wants to implement Safewards and direct limited resources to only a few implementation determinants, these three may be worth considering. Data representing levels of external health system and organizational contexts were rare. In contrast, data relating to local (ward)-level contexts was highly represented which may reflect Safewards's focus on quality improvement strategies on a local rather than organizational level. © 2023 The Authors. International Journal of Mental Health Nursing published by John Wiley & Sons Australia, Ltd.

In many situations, probabilistic predictors have replaced conformal classifiers. The main reason is arguably that the set predictions of conformal classifiers, with the accompanying significance level, are hard to interpret. In this paper, we demonstrate how conformal classification can be used as a basis for a classifier with reject option. Specifically, we introduce and evaluate two algorithms that are able to perfectly estimate accuracy or precision for a set of test instances, in a classifier with reject scenario. In the empirical investigation, the suggested algorithms are shown to clearly outperform both calibrated and uncalibrated probabilistic predictors.

Score-based explainable machine-learning techniques are often used to understand the logic behind black-box models. However, such explanation techniques are often computationally expensive, which limits their application in time-critical contexts. Therefore, we propose and investigate the use of computationally less costly regression models for approximating the output of score-based explanation techniques, such as SHAP. Moreover, validity guarantees for the approximated values are provided by the employed inductive conformal prediction framework. We propose several non-conformity measures designed to take the difficulty of approximating the explanations into account while keeping the computational cost low. We present results from a large-scale empirical investigation, in which the approximate explanations generated by our proposed models are evaluated with respect to efficiency (interval size). The results indicate that the proposed method can significantly improve execution time compared to the fast version of SHAP, TreeSHAP. The results also suggest that the proposed method can produce tight intervals, while providing validity guarantees. Moreover, the proposed approach allows for comparing explanations of different approximation methods and selecting a method based on how informative (tight) are the predicted intervals.

KNIME is an end-to-end software platform for data science with an open-source analytics platform for creating solutions and a commercial server solution for productionization. Conformal classification and regression have previously been implemented in KNIME. We extend the conformal prediction package with added support for conformal predictive systems, taking inspiration from the interface of the Crepes package in Python. The paper demonstrates some typical use cases for conformal predictive systems. Furthermore, the paper also illustrates how to create Mondrian conformal predictors using the KNIME implementation. All examples are publicly available, and the package is1 available through KNIME's official software repositories.

The manufacturing industry are increasingly turning to artificial intelligence (AI), particularly machine learning (ML), to improve their operations and decision-making. Predictive modelling and ML hold significant promise in revolutionising forecasting and assessment activities by offering improved decision support for quicker and more reliable decisions. However, the preliminary results of the current multidisciplinary and interactive research project PredMod (short for predictive modelling) empirically shows that there are still many challenges to overcome when implementing predictive modelling and ML to produce forecasts and other assessments, such as capacity needs, in the manufacturing industry. The purpose of this paper is to enhance managerial comprehension and awareness of challenges associated with using predictive modelling and machine learning to produce forecasts and assessments within the manufacturing industry. Based on the empirically identified challenges, the paper also provides some practical lessons learned and articulate key questions that should guide predictive modelling projects within the manufacturing industry., AFAIR, OnTime, PredMod

Product returns are not only costly for e-tailers, but the unnecessary transports also impact the environment. Consequently, online retailers have started to formulate policies to reduce the number of returns. Determining when and how to act is, however, a delicate matter, since a too harsh approach may lead to not only the order being cancelled, but also the customer leaving the business. Being able to accurately predict which orders that will lead to a return would be a strong tool, guiding which actions to be taken. This paper addresses the problem of data-driven product return prediction, by conducting a case study using a large real-world data set. The main results are that well-calibrated probabilistic predictors are essential for providing predictions with high precision and reasonable recall. This implies that utilizing calibrated models to predict some instances, while rejecting to predict others can be recommended. In practice, this would make it possible for a decision-maker to only act upon a subset of all predicted returns, where the risk of a return is very high., ©2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.This research is a part of the industrial graduate research school in digital retailing (INSiDR) at the University of Borås, funded by The Swedish Knowledge Foundation, grants nr. 20160035, 20170215., INSiDR

Xylan that comprises roughly 25% of hardwood biomass is undesirable in biorefinery applications involving saccharification and fermentation. Efforts to reduce xylan levels have therefore been made in many species, usually resulting in improved saccharification. However, such modified plants have not yet been tested under field conditions. Here we evaluate the field performance of transgenic hybrid aspen lines with reduced xylan levels and assess their usefulness as short-rotation feedstocks for biorefineries. Three types of transgenic lines were tested in four-year field tests with RNAi constructs targeting either Populus GT43 clades B and C (GT43BC) corresponding to Arabidopsis clades IRX9 and IRX14, respectively, involved in xylan backbone biosynthesis, GATL1.1 corresponding to AtGALT1 involved in xylan reducing end sequence biosynthesis, or ASPR1 encoding an atypical aspartate protease. Their productivity, wood quality traits, and saccharification efficiency were analyzed. The only lines differing significantly from the wild type with respect to growth and biotic stress resistance were the ASPR1 lines, whose stems were roughly 10% shorter and narrower and leaves showed increased arthropod damage. GT43BC lines exhibited no growth advantage in the field despite their superior growth in greenhouse experiments. Wood from the ASPR1 and GT43BC lines had slightly reduced density due to thinner cell walls and, in the case of ASPR1, larger cell diameters. The xylan was less extractable by alkali but more hydrolysable by acid, had increased glucuronosylation, and its content was reduced in all three types of transgenic lines. The hemicellulose size distribution in the GALT1.1 and ASPR1 lines was skewed towards higher molecular mass compared to the wild type. These results provide experimental evidence that GATL1.1 functions in xylan biosynthesis and suggest that ASPR1 may regulate this process. In saccharification without pretreatment, lines of all three constructs provide

A standard classifier is forced to predict the label of every test instance, even when confidence in the predictions is very low. In many scenarios, it would, however, be better to avoid making these predictions, maybe leaving them to a human expert. A classifier with that alternative is referred to as a classifier with reject option. In this paper, we propose an algorithm that, for a particular data set, automatically suggests a number of accuracy levels, which it will be able to meet perfectly, using a classifier with reject option. Since the basis of the suggested algorithm is conformal prediction, it comes with strong validity guarantees. The experimentation, using 25 publicly available two-class data sets, confirms that the algorithm obtains empirical accuracies very close to the requested levels. In addition, in an outright comparison with probabilistic predictors, including models calibrated with Platt scaling, the suggested algorithm clearly outperforms the alternatives.

Predictive models used in Decision Support Systems (DSS) are often requested to explain the reasoning to users. Explanations of instances consist of two parts; the predicted label with an associated certainty and a set of weights, one per feature, describing how each feature contributes to the prediction for the particular instance. In techniques like Local Interpretable Model-agnostic Explanations (LIME), the probability estimate from the underlying model is used as a measurement of certainty; consequently, the feature weights represent how each feature contributes to the probability estimate. It is, however, well-known that probability estimates from classifiers are often poorly calibrated, i.e., the probability estimates do not correspond to the actual probabilities of being correct. With this in mind, explanations from techniques like LIME risk becoming misleading since the feature weights will only describe how each feature contributes to the possibly inaccurate probability estimate. This paper investigates the impact of calibrating predictive models before applying LIME. The study includes 25 benchmark data sets, using Random forest and Extreme Gradient Boosting (xGBoost) as learners and Venn-Abers and Platt scaling as calibration methods. Results from the study show that explanations of better calibrated models are themselves better calibrated, with ECE and log loss for the explanations after calibration becoming more conformed to the model ECE and log loss. The conclusion is that calibration makes the models and the explanations better by accurately representing reality.

Being able to understand the logic behind predictions or recommendations on the instance level is at the heart of trustworthy machine learning models. Inherently interpretable models make this possible by allowing inspection and analysis of the model itself, thus exhibiting the logic behind each prediction, while providing an opportunity to gain insights about the underlying domain. Another important criterion for trustworthiness is the model’s ability to somehow communicate a measure of confidence in every specific prediction or recommendation. Indeed, the overall goal of this paper is to produce highly informative models that combine interpretability and algorithmic confidence. For this purpose, we introduce conformal predictive distribution trees, which is a novel form of regression trees where each leaf contains a conformal predictive distribution. Using this representation language, the proposed approach allows very versatile analyses of individual leaves in the regression trees. Specifically, depending on the chosen level of detail, the leaves, in addition to the normal point predictions, can provide either cumulative distributions or prediction intervals that are guaranteed to be well-calibrated. In the empirical evaluation, the suggested conformal predictive distribution trees are compared to the well-established conformal regressors, thus demonstrating the benefits of the enhanced representation.

Xylan that comprises roughly 25% of hardwood biomass is undesirable in biorefinery applications involving saccharification and fermentation. Efforts to reduce xylan levels have therefore been made in many species, usually resulting in improved saccharification. However, such modified plants have not yet been tested under field conditions. Here we evaluate the field performance of transgenic hybrid aspen lines with reduced xylan levels and assess their usefulness as short-rotation feedstocks for biorefineries. Three types of transgenic lines were tested in four-year field tests with RNAi constructs targeting either Populus GT43 clades B and C (GT43BC) corresponding to Arabidopsis clades IRX9 and IRX14, respectively, involved in xylan backbone biosynthesis, GATL1.1 corresponding to AtGALT1 involved in xylan reducing end sequence biosynthesis, or ASPR1 encoding an atypical aspartate protease. Their productivity, wood quality traits, and saccharification efficiency were analyzed. The only lines differing significantly from the wild type with respect to growth and biotic stress resistance were the ASPR1 lines, whose stems were roughly 10% shorter and narrower and leaves showed increased arthropod damage. GT43BC lines exhibited no growth advantage in the field despite their superior growth in greenhouse experiments. Wood from the ASPR1 and GT43BC lines had slightly reduced density due to thinner cell walls and, in the case of ASPR1, larger cell diameters. The xylan was less extractable by alkali but more hydrolysable by acid, had increased glucuronosylation, and its content was reduced in all three types of transgenic lines. The hemicellulose size distribution in the GALT1.1 and ASPR1 lines was skewed towards higher molecular mass compared to the wild type. These results provide experimental evidence that GATL1.1 functions in xylan biosynthesis and suggest that ASPR1 may regulate this process. In saccharification without pretreatment, lines of all three constructs provide

Trees constitute promising renewable feedstocks for biorefinery using biochemical conversion, but their recalcitrance restricts their attractiveness for the industry. To obtain trees with reduced recalcitrance, large-scale genetic engineering experiments were performed in hybrid aspen blindly targeting genes expressed during wood formation and 32 lines representing seven constructs were selected for characterization in the field. Here we report phenotypes of five-year old trees considering 49 traits related to growth and wood properties. The best performing construct considering growth and glucose yield in saccharification with acid pretreatment had suppressed expression of the gene encoding an uncharacterized 2-oxoglutarate-dependent dioxygenase (2OGD). It showed minor changes in wood chemistry but increased nanoporosity and glucose conversion. Suppressed levels of SUCROSE SYNTHASE, (SuSy), CINNAMATE 4-HYDROXYLASE (C4H) and increased levels of GTPase activating protein for ADP-ribosylation factor ZAC led to significant growth reductions and anatomical abnormalities. However, C4H and SuSy constructs greatly improved glucose yields in saccharification without and with pretreatment, respectively. Traits associated with high glucose yields were different for saccharification with and without pretreatment. While carbohydrates, phenolics and tension wood contents positively impacted the yields without pretreatment and growth, lignin content and S/G ratio were negative factors, the yields with pretreatment positively correlated with S lignin and negatively with carbohydrate contents. The genotypes with high glucose yields had increased nanoporosity and mGlcA/Xyl ratio, and some had shorter polymers extractable with subcritical water compared to wild-type. The pilot-scale industrial-like pretreatment of best-performing 2OGD construct confirmed its superior sugar yields, supporting our strategy.

Trees constitute promising renewable feedstocks for biorefinery using biochemical conversion, but their recalcitrance restricts their attractiveness for the industry. To obtain trees with reduced recalcitrance, large-scale genetic engineering experiments were performed in hybrid aspen blindly targeting genes expressed during wood formation and 32 lines representing seven constructs were selected for characterization in the field. Here we report phenotypes of five-year old trees considering 49 traits related to growth and wood properties. The best performing construct considering growth and glucose yield in saccharification with acid pretreatment had suppressed expression of the gene encoding an uncharacterized 2-oxoglutarate-dependent dioxygenase (2OGD). It showed minor changes in wood chemistry but increased nanoporosity and glucose conversion. Suppressed levels of SUCROSE SYNTHASE, (SuSy), CINNAMATE 4-HYDROXYLASE (C4H) and increased levels of GTPase activating protein for ADP-ribosylation factor ZAC led to significant growth reductions and anatomical abnormalities. However, C4H and SuSy constructs greatly improved glucose yields in saccharification without and with pretreatment, respectively. Traits associated with high glucose yields were different for saccharification with and without pretreatment. While carbohydrates, phenolics and tension wood contents positively impacted the yields without pretreatment and growth, lignin content and S/G ratio were negative factors, the yields with pretreatment positively correlated with S lignin and negatively with carbohydrate contents. The genotypes with high glucose yields had increased nanoporosity and mGlcA/Xyl ratio, and some had shorter polymers extractable with subcritical water compared to wild-type. The pilot-scale industrial-like pretreatment of best-performing 2OGD construct confirmed its superior sugar yields, supporting our strategy.

While local explanations for AI models can offer insights into individual predictions, such as feature importance, they are plagued by issues like instability. The unreliability of feature weights, often skewed due to poorly calibrated ML models, deepens these challenges. Moreover, the critical aspect of feature importance uncertainty remains mostly unaddressed in Explainable AI (XAI). The novel feature importance explanation method presented in this paper, called Calibrated Explanations (CE), is designed to tackle these issues head-on. Built on the foundation of Venn-Abers, CE not only calibrates the underlying model but also delivers reliable feature importance explanations with an exact definition of the feature weights. CE goes beyond conventional solutions by addressing output uncertainty. It accomplishes this by providing uncertainty quantification for both feature weights and the model's probability estimates. Additionally, CE is model-agnostic, featuring easily comprehensible conditional rules and the ability to generate counterfactual explanations with embedded uncertainty quantification. Results from an evaluation with 25 benchmark datasets underscore the efficacy of CE, making it stand as a fast, reliable, stable, and robust solution., Comment: 19 pages, 6 figures, 3 tables, submitted to journal

Low nutrient availability often limits productivity in northern forests. In a nutrient optimisation trial, we investigated the effects of fertilisation and irrigation on soil moisture, leaf area index (LAI) as well as height and radial growth in 25-year-old stands of pedunculate and sessile oak (Quercus robur L., Q. petraea (Matt.) Liebl.) growing on abandoned farmland in southwestern Sweden. Control (C), fertilisation (F), irrigation (I), and irrigation +fertilisation (IF) treatments were arranged in a randomized complete block design. End of growing season analysis of foliar nutrients guided the quantitative composition of next year’s fertiliser mix. Volumetric soil moisture (VWC) was significantly higher in the I and IF treatments compared to the C and F treated stands of both oak species. We did not observe a fertiliser-related reduction in VWC (except for 2015, when VWC in F- treated Q. robur stands was significantly lower than the control by about 18 %). This is in line with the unaffected LAI estimates (5.3–5.9) suggesting no stimulation of leaf production that could drive increases in transpiration with subsequent soil moisture depletion. There was no treatment ×year interaction for any of the growth-related variables. Treatments had no significant effects on basal area growth, which increased annually by 1.72 and 1.54 m2 ha-1 on average for Q. petraea and Q. robur, respectively. Pre-treatment height differences in Q. petraea stands (7–12 % taller trees in the C and IF plots) persisted throughout the study resulting in significant effects, while no significant differences in height occurred in Q. robur. Periodic annual volume increment varied more strongly following drier periods but there were no significant differences among treatments. Our findings indicate that fertilisation causes no or only minor increases in oak water use, suggesting that nutrient addition in oak stands within this precipitation regime does not require simultaneous irrigation. Most im

Low nutrient availability often limits productivity in northern forests. In a nutrient optimisation trial, we investigated the effects of fertilisation and irrigation on soil moisture, leaf area index (LAI) as well as height and radial growth in 25-year-old stands of pedunculate and sessile oak (Quercus robur L., Q. petraea (Matt.) Liebl.) growing on abandoned farmland in southwestern Sweden. Control (C), fertilisation (F), irrigation (I), and irrigation +fertilisation (IF) treatments were arranged in a randomized complete block design. End of growing season analysis of foliar nutrients guided the quantitative composition of next year’s fertiliser mix. Volumetric soil moisture (VWC) was significantly higher in the I and IF treatments compared to the C and F treated stands of both oak species. We did not observe a fertiliser-related reduction in VWC (except for 2015, when VWC in F- treated Q. robur stands was significantly lower than the control by about 18 %). This is in line with the unaffected LAI estimates (5.3–5.9) suggesting no stimulation of leaf production that could drive increases in transpiration with subsequent soil moisture depletion. There was no treatment ×year interaction for any of the growth-related variables. Treatments had no significant effects on basal area growth, which increased annually by 1.72 and 1.54 m2 ha-1 on average for Q. petraea and Q. robur, respectively. Pre-treatment height differences in Q. petraea stands (7–12 % taller trees in the C and IF plots) persisted throughout the study resulting in significant effects, while no significant differences in height occurred in Q. robur. Periodic annual volume increment varied more strongly following drier periods but there were no significant differences among treatments. Our findings indicate that fertilisation causes no or only minor increases in oak water use, suggesting that nutrient addition in oak stands within this precipitation regime does not require simultaneous irrigation. Most im

Product returns are not only costly for e-tailers, but the unnecessary transports also impact the environment. Consequently, online retailers have started to formulate policies to reduce the number of returns. Determining when and how to act is, however, a delicate matter, since a too harsh approach may lead to not only the order being cancelled, but also the customer leaving the business. Being able to accurately predict which orders that will lead to a return would be a strong tool, guiding which actions to be taken. This paper addresses the problem of data-driven product return prediction, by conducting a case study using a large real-world data set. The main results are that well-calibrated probabilistic predictors are essential for providing predictions with high precision and reasonable recall. This implies that utilizing calibrated models to predict some instances, while rejecting to predict others can be recommended. In practice, this would make it possible for a decision-maker to only act upon a subset of all predicted returns, where the risk of a return is very high.

Product returns are not only costly for e-tailers, but the unnecessary transports also impact the environment. Consequently, online retailers have started to formulate policies to reduce the number of returns. Determining when and how to act is, however, a delicate matter, since a too harsh approach may lead to not only the order being cancelled, but also the customer leaving the business. Being able to accurately predict which orders that will lead to a return would be a strong tool, guiding which actions to be taken. This paper addresses the problem of data-driven product return prediction, by conducting a case study using a large real-world data set. The main results are that well-calibrated probabilistic predictors are essential for providing predictions with high precision and reasonable recall. This implies that utilizing calibrated models to predict some instances, while rejecting to predict others can be recommended. In practice, this would make it possible for a decision-maker to only act upon a subset of all predicted returns, where the risk of a return is very high., ©2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.This research is a part of the industrial graduate research school in digital retailing (INSiDR) at the University of Borås, funded by The Swedish Knowledge Foundation, grants nr. 20160035, 20170215., INSiDR

Product returns are not only costly for e-tailers, but the unnecessary transports also impact the environment. Consequently, online retailers have started to formulate policies to reduce the number of returns. Determining when and how to act is, however, a delicate matter, since a too harsh approach may lead to not only the order being cancelled, but also the customer leaving the business. Being able to accurately predict which orders that will lead to a return would be a strong tool, guiding which actions to be taken. This paper addresses the problem of data-driven product return prediction, by conducting a case study using a large real-world data set. The main results are that well-calibrated probabilistic predictors are essential for providing predictions with high precision and reasonable recall. This implies that utilizing calibrated models to predict some instances, while rejecting to predict others can be recommended. In practice, this would make it possible for a decision-maker to only act upon a subset of all predicted returns, where the risk of a return is very high., ©2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.This research is a part of the industrial graduate research school in digital retailing (INSiDR) at the University of Borås, funded by The Swedish Knowledge Foundation, grants nr. 20160035, 20170215., INSiDR

Product returns are not only costly for e-tailers, but the unnecessary transports also impact the environment. Consequently, online retailers have started to formulate policies to reduce the number of returns. Determining when and how to act is, however, a delicate matter, since a too harsh approach may lead to not only the order being cancelled, but also the customer leaving the business. Being able to accurately predict which orders that will lead to a return would be a strong tool, guiding which actions to be taken. This paper addresses the problem of data-driven product return prediction, by conducting a case study using a large real-world data set. The main results are that well-calibrated probabilistic predictors are essential for providing predictions with high precision and reasonable recall. This implies that utilizing calibrated models to predict some instances, while rejecting to predict others can be recommended. In practice, this would make it possible for a decision-maker to only act upon a subset of all predicted returns, where the risk of a return is very high., ©2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.This research is a part of the industrial graduate research school in digital retailing (INSiDR) at the University of Borås, funded by The Swedish Knowledge Foundation, grants nr. 20160035, 20170215., INSiDR

Artificial Intelligence (AI) is often an integral part of modern decision support systems. The best-performing predictive models used in AI-based decision support systems lack transparency. Explainable Artificial Intelligence (XAI) aims to create AI systems that can explain their rationale to human users. Local explanations in XAI can provide information about the causes of individual predictions in terms of feature importance. However, a critical drawback of existing local explanation methods is their inability to quantify the uncertainty associated with a feature's importance. This paper introduces an extension of a feature importance explanation method, Calibrated Explanations, previously only supporting classification, with support for standard regression and probabilistic regression, i.e., the probability that the target is above an arbitrary threshold. The extension for regression keeps all the benefits of Calibrated Explanations, such as calibration of the prediction from the underlying model with confidence intervals, uncertainty quantification of feature importance, and allows both factual and counterfactual explanations. Calibrated Explanations for standard regression provides fast, reliable, stable, and robust explanations. Calibrated Explanations for probabilistic regression provides an entirely new way of creating probabilistic explanations from any ordinary regression model, allowing dynamic selection of thresholds. The method is model agnostic with easily understood conditional rules. An implementation in Python is freely available on GitHub and for installation using both pip and conda, making the results in this paper easily replicable., Comment: 34 pages, 13 figures (resubmitted draft after minor revision)

Score-based explainable machine-learning techniques are often used to understand the logic behind black-box models. However, such explanation techniques are often computationally expensive, which limits their application in time-critical contexts. Therefore, we propose and investigate the use of computationally less costly regression models for approximating the output of score-based explanation techniques, such as SHAP. Moreover, validity guarantees for the approximated values are provided by the employed inductive conformal prediction framework. We propose several non-conformity measures designed to take the difficulty of approximating the explanations into account while keeping the computational cost low. We present results from a large-scale empirical investigation, in which the approximate explanations generated by our proposed models are evaluated with respect to efficiency (interval size). The results indicate that the proposed method can significantly improve execution time compared to the fast version of SHAP, TreeSHAP. The results also suggest that the proposed method can produce tight intervals, while providing validity guarantees. Moreover, the proposed approach allows for comparing explanations of different approximation methods and selecting a method based on how informative (tight) are the predicted intervals., Comment: 20 pages, 14 figures, The 12th Symposium on Conformal and Probabilistic Prediction with Applications (COPA 2023)

When using machine learning for fault detection, a common problem is the fact that most data sets are very unbalanced, with the minority class (a fault) being the interesting one. In this paper, we investigate the usage of Venn-Abers predictors, looking specifically at the effect on the minority class predictions. A key property of Venn-Abers predictors is that they output well-calibrated probability intervals. In the experiments, we apply Venn-Abers calibration to decision trees, random forests and XGBoost models, showing how both overconfident and underconfident models are corrected. In addition, the benefit of using the valid probability intervals produced by Venn-Abers for decision support is demonstrated. When using techniques producing opaque underlying models, e.g., random forest and XGBoost, each prediction will consist of not only the label, but also a valid probability interval, where the width is an indication of the confidence in the estimate. Adding Venn-Abers on top of a decision tree allows inspection and analysis of the model, to understand both the underlying relationship, and finding out in which parts of feature space that the model is accurate and/or confident.

Tools for understanding and explaining complex predictive models are critical for user acceptance and trust. One such tool is rule extraction, i.e., approximating opaque models with less powerful but interpretable models. Pedagogical (or black-box) rule extraction, where the interpretable model is induced using the original training instances, but with the predictions from the opaque model as targets, has many advantages compared to the decompositional (white-box) approach. Most importantly, pedagogical methods are agnostic to the kind of opaque model used, and any learning algorithm producing interpretable models can be employed for the learning step. The pedagogical approach has, however, one main problem, clearly limiting its utility. Specifically, while the extracted models are trained to mimic the opaque, there are absolutely no guarantees that this will transfer to novel data. This potentially low test set fidelity must be considered a severe drawback, in particular when the extracted models are used for explanation and analysis. In this paper, a novel approach, solving the problem with test set fidelity by utilizing the conformal prediction framework, is suggested for extracting interpretable regression models from opaque models. The extracted models are standard regression trees, but augmented with valid prediction intervals in the leaves. Depending on the exact setup, the use of conformal prediction guarantees that either the test set fidelity or the test set accuracy will be equal to a preset confidence level, in the long run. In the extensive empirical investigation, using 20 publicly available data sets, the validity of the extracted models is demonstrated. In addition, it is shown how normalization can be used to provide individualized prediction intervals, thus providing highly informative extracted models., QC 20220325

Customer churn is one of the most challenging problems for digital retailers. With significantly higher costs for acquiring new customers than retaining existing ones, knowledge about which customers are likely to churn becomes essential. This paper reports a case study where a data-driven approach to churn prediction is used for predicting churners and gaining insights about the problem domain. The real-world data set used contains approximately 200 000 customers, describing each customer using more than 50 features. In the pre-processing, exploration, modeling and analysis, attributes related to recency, frequency, and monetary concepts are identified and utilized. In addition, correlations and feature importance are used to discover and understand churn indicators. One important finding is that the churn rate highly depends on the number of previous purchases. In the segment consisting of customers with only one previous purchase, more than 75% will churn, i.e., not make another purchase in the coming year. For customers with at least four previous purchases, the corresponding churn rate is around 25%. Further analysis shows that churning customers in general, and as expected, make smaller purchases and visit the online store less often. In the experimentation, three modeling techniques are evaluated, and the results show that, in particular, Gradient Boosting models can predict churners with relatively high accuracy while obtaining a good balance between precision and recall., INSiDR

The evaluation of explanation methods has become a significant issue in explainable artificial intelligence (XAI) due to the recent surge of opaque AI models in decision support systems (DSS). Explanations are essential for bias detection and control of uncertainty since most accurate AI models are opaque with low transparency and comprehensibility. There are numerous criteria to choose from when evaluating explanation method quality. However, since existing criteria focus on evaluating single explanation methods, it is not obvious how to compare the quality of different methods. In this paper, we have conducted a semi-systematic meta-survey over fifteen literature surveys covering the evaluation of explainability to identify existing criteria usable for comparative evaluations of explanation methods. The main contribution in the paper is the suggestion to use appropriate trust as a criterion to measure the outcome of the subjective evaluation criteria and consequently make comparative evaluations possible. We also present a model of explanation quality aspects. In the model, criteria with similar definitions are grouped and related to three identified aspects of quality; model, explanation, and user. We also notice four commonly accepted criteria (groups) in the literature, covering all aspects of explanation quality: Performance, appropriate trust, explanation satisfaction, and fidelity. We suggest the model be used as a chart for comparative evaluations to create more generalisable research in explanation quality., This research is partly founded by the Swedish Knowledge Foundation through the Industrial Research School INSiDR.

Rules output by explainable machine learning techniques naturally come with a degree of uncertainty, as the complex functionality of the underlying black-box model often can be difficult to approximate by a single, interpretable rule. However, the uncertainty of these approximations is not properly quantified by current explanatory techniques. The use of Venn prediction is here proposed and investigated as a means to quantify the uncertainty of the explanations and thereby also allow for competing explanation techniques to be evaluated with respect to their relative uncertainty. A number of metrics of rule explanation quality based on uncertainty are proposed and discussed, including metrics that capture the tendency of the explanations to predict the correct outcome of a black-box model on new instances, how informative (tight) the produced intervals are, and how certain a rule is when predicting one class. An empirical investigation is presented, in which explanations produced by the state-of-the-art technique Anchors are compared to explanatory rules obtained from association rule mining. The results suggest that the association rule mining approach may provide explanations with less uncertainty towards the correct label, as predicted by the black-box model, compared to Anchors. The results also show that the explanatory rules obtained through association rule mining result in tighter intervals and are closer to either one or zero compared to Anchors, i.e., they are more certain towards a specific class label., QC 20230821

QC 20230908

Customer churn is one of the most challenging problems for digital retailers. With significantly higher costs for acquiring new customers than retaining existing ones, knowledge about which customers are likely to churn becomes essential. This paper reports a case study where a data-driven approach to churn prediction is used for predicting churners and gaining insights about the problem domain. The real-world data set used contains approximately 200 000 customers, describing each customer using more than 50 features. In the pre-processing, exploration, modeling and analysis, attributes related to recency, frequency, and monetary concepts are identified and utilized. In addition, correlations and feature importance are used to discover and understand churn indicators. One important finding is that the churn rate highly depends on the number of previous purchases. In the segment consisting of customers with only one previous purchase, more than 75% will churn, i.e., not make another purchase in the coming year. For customers with at least four previous purchases, the corresponding churn rate is around 25%. Further analysis shows that churning customers in general, and as expected, make smaller purchases and visit the online store less often. In the experimentation, three modeling techniques are evaluated, and the results show that, in particular, Gradient Boosting models can predict churners with relatively high accuracy while obtaining a good balance between precision and recall.