Search

The adoption of data science brings vast benefits to Small and Medium-sized Enterprises (SMEs) including business productivity, economic growth, innovation and job creation. Data science can support SMEs to optimise production processes, anticipate customers' needs, predict machinery failures and deliver efficient smart services. Businesses can also harness the power of artificial intelligence (AI) and big data, and the smart use of digital technologies to enhance productivity and performance, paving the way for innovation. However, integrating data science decisions into an SME requires both skills and IT investments. In most cases, such expenses are beyond the means of SMEs due to their limited resources and restricted access to financing. This paper presents trends and challenges towards effective data-driven decision making for organisations based on a 3-year long study which covered more than 85 UK SMEs, mostly from the West Midlands region of England. In particular, this study attempts to find answers to several key research questions around data science and AI adoption among UK SMEs, and the advantages of digitalisation and data-driven decision making, as well as the challenges hindering their effective utilisation of these technologies. We also present two case studies that demonstrate the potential of digitisation and data science, and use these as examples to unveil challenges and showcase the wealth of currently available opportunities for SMEs. [ABSTRACT FROM AUTHOR]

The author comments on an article published within the issue which explores the gap between how marketing research is taught in business schools in Great Britain and how the practitioner world of market research is evolving. Topics covered include the challenge of re-aligning the academic and practitioner communities in marketing research, and the need to change in the curriculum as well as a new name for the sector that reflects the trend from surveys to big data.

This paper first examines the UK Department for Transport's top-level planning for transport big data and UK rail data access, including the Department's proposed directions for big data applications, transport data sets and data fusion. It then summarizes such information as data statistics, Data Portal Services and data application developed and provided to the public by UK's rail regulator Office of Rail and Road and UK's rail operator Network Rail. It finally puts forward suggestions on the application and development of the big data in China's rail transport industry from the perspective of building the rail transport data set, constructing the data portal for rail transport, and promoting the opening sharing of relevant data. [ABSTRACT FROM AUTHOR]

Reviews of official statistics for UK housing have noted that developments have not kept pace with real‐world change, particularly the rapid growth of private renting. This paper examines the potential value of big data in this context. We report on the construction of a dataset from the on‐line adverts of one national lettings agency, describing the content of the dataset and efforts to validate it against external sources. The paper specifically examines what these data might add to our understanding of changing volumes and rents in the private rented sector. Fluctuations in market share across advertising platforms make assessment of volume problematic, while rental prices appear more robust through comparison with other reference information. Focussing on one urban area, we illustrate how the dataset can shed new light on local changes. Lastly, we discuss the issues involved in making more routine use of this kind of data. [ABSTRACT FROM AUTHOR]

This paper explores how liquidity in the UK rental markets reacts to variations in demand across time and space. We employ a survival analysis approach with a non-parametric hazard rate to investigate whether the probability of a property to exit the market changes across calendar months. Our unique dataset comes from Zoopla.com and contains 300,198 rental listings in 13 major UK university cities over the 2015–2017 period. Our results suggest that the probability of exit is lower during the winter season compared to summer. This could be explained by students' higher housing demand at the start of the academic term. The results become more pronounced (i.e. the seasonal difference is higher) when the distance between marketed property and university campuses is taken into account. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to explain the rise of geospatial data, its importance for business and some of the problems associated with its development and use. Design/methodology/approach: The paper reviews a certain amount of previously published literature but is based mainly on analysis of the very large number of responses to a consultation paper on geospatial data published by the UK Government. Findings: The findings are that while there is strong appreciation of the potential benefits of using geospatial data, there are many barriers to the development, sharing and use of geospatial data, ranging from problems of incompatibility in data definitions and systems to regulatory issues. The implication for governments and for providers and users of geospatial data relates to the need to take a long-term approach to planning in resolving the issues identified. Research limitations/implications: The research findings are limited to the UK, but similar findings would be likely in any other large Western country. Practical implications: This paper confirms the need for a strong and coherent approach to the planning of geospatial data and systems for the establishment of a clear basis for the different parties to work together and the need to clearly separate the roles of the government in establishing frameworks and standards and the role of the private sector in developing applications and solutions. Social implications: Society is increasingly dependent on the use of geospatial data, in improving living standards and dealing with social problems. The recommendations identified in this paper, if followed, will facilitate these improvements. Originality/value: The value of this paper is the tight synthesis that it provides of a wide ranging and complex range of responses to the UK Government consultation and placing these responses in the wider context of the development of geospatial data. [ABSTRACT FROM AUTHOR]

This paper investigates the predictive ability of a brand new dataset that is based on big unstructured data published by the UK Office for National Statistics as "Faster Indicators of UK Economic Activity." We consider some indicative ways for use in macroeconomic nowcasting. Even though the ONS confirms that the newly introduced big data‐based indicators are not constructed with forecasting purposes in mind, and applied researchers should be cautious when using them in this way, a simple out‐of‐sample nowcasting exercise reveals partial evidence that this dataset has some predictive power over GDP growth. Our results, which show a positive and encouraging first step towards the use of this type of data, suggest that national statistics agencies should allocate more resources in constructing big data‐based databases. [ABSTRACT FROM AUTHOR]

This research is devoted to the determination of hidden dependencies between the flow of particles that come from the Sun and precipitation-induced floods in the United Kingdom (UK). The analysis covers 20 flood events during the period from October 2001 to December 2019. The parameters of solar activity were used as model input data, while precipitations data in the period 10 days before and during each flood event were used as model output. The time lag of 0–9 days was taken into account in the research. Correlation analysis was conducted to determine the degree of randomness for the time series of input and output parameters. For establishing a potential causative link, machine learning classification predictive modeling was applied. Two approaches, the decision tree, and the random forest were used. We analyzed the accuracy of classification models forecast from 0 to 9 days in advance. It was found that the most important factors for flood forecasting are proton density with a time lag of 9, differential proton flux in the range of 310–580 keV, and ion temperature. Research in this paper has shown that the decision tree model is more accurate and adequate in predicting the appearance of precipitation-induced floods up to 9 days ahead with an accuracy of 91%. The results of this study confirmed that by increasing technical capabilities, using improved machine learning techniques and large data sets, it is possible to improve the understanding of the physical link between the solar wind and tropospheric weather and help improve severe weather forecasting. [ABSTRACT FROM AUTHOR]

In democratic societies, the political process ultimately is about making value judgements. Comparative cultural policy research indicates different value orientations may be behind cultural policies of different nations. It has also indicated developments that are common, such as democratisation of culture, neoliberalisation of politics and globalisation. As of yet, such value changes have not been studied at the level of cultural policy documents analysed as text. This article proposes a methodology to study value changes behind cultural policies over time and across nations. Based in the "pragmatic sociology" of Boltanski, Thévenot, and Chiapello, the article presents a big data methodology to uncover value changes of policy documents over time, between different policy agents, and across nations using material from the UK and the Netherlands. The paper explains the methodology, discusses the implications of the preliminary outcomes and provides suggestions for further comparative policy analyses. [ABSTRACT FROM AUTHOR]

Big data starts booming in 2013 and has multiple applications in all walks of life. In such an environment, big data for information technology (BDI) and decision making (BDD) have formed some hot topics in common. This paper reviews the body of BDI and BDD research studies from 1994 to 2020, using bibliometrics analysis. The aim of this paper is to explore the current status, the correlation between BDI and BDD, the future trends and challenges. From time and space dimensions, CiteSpace and VOS viewer are used to obtain the annual trends of documents, the distribution of countries and sources, the citations and the h-index of BDI and BDD. The top three productive countries are the USA, China and the UK. From the perspective of h-index, the USA and the UK are at the forefront of the world. The value of big data is realized through information acquisition, storage, analysis, expression transmission and service sharing technologies, and the decision-making techniques exist throughout the process of big data analysis. "Business" and "Information science library science" are the latest hotspots of BDI. The appliances in the organization, supply chain management, education, and the environment are recent themes of BDD. Big data technology processing capabilities and network security issues are the main challenges in the future. This study contributes to the body of knowledge on BDI and BDD, and hops to help in understanding the evolution of them in relevant fields. [ABSTRACT FROM AUTHOR]

OECD countries have established statistical collections to ensure quality within Early Childhood Education and Care (ECEC). Focusing on one part of ECEC - preschool 'childcare services' - this paper critically reviews statistical collections specifically designed to measure childcare patterns in England alongside UK data collected for other purposes which can be used to examine childcare patterns. The paper evaluates how far these data provide a reliable basis for examining the childcare workforce, how well childcare usage and provision patterns can be analysed and the degree to which the data provide comparable geographical coverage. Results show analysis is restricted by the various ways data-sets count and classify occupations. Differences in geographical coverage make them difficult to compare. More refinement of occupation categories would make existing sources more useful. The themes discussed here are relevant for other countries seeking to understand how best to utilise their statistical collections for examining childcare patterns. [ABSTRACT FROM AUTHOR]

In this paper we make a case for 'Little Data', which is real-time, self-collected, idiosyncratic datasets maintained by individuals about themselves on myriad topics. We develop and offer a methodology for combining these messy, highly personal insights, to make deductive observations about collective practices. In testing this approach, we use the case study of the 2020–21 stay-at-home orders imposed in the U.S.A., U.K., and Western Europe during the Coronavirus pandemic to operationalise and demonstrate the applicability of this method. Our main finding is to show that whilst stay-at-home orders did have a significant impact on habits during the COVID-19 pandemic, these changes were often counterintuitive, of an insightful nature on topics that would otherwise not be investigated, and always short-lived. Our main contribution is to present Little Data, despite and because of its fragmented and disparate nature, as a viable and useful tool to understand personal habits at finite junctures. [ABSTRACT FROM AUTHOR]

The Snowden revelations concerning the use of bulk surveillance have uncovered shortcomings in the existing intelligence oversight architectures in several leading democracies and confronted them with a variety of new challenges generated by rapid technological advances. The impact of the disclosures has also been reflected in scholarship, namely in the way intelligence oversight is being reconceptualized as a broader form of governance beyond legal compliance. This article examines the case of the UK and investigates instances when the two main oversight institutions, namely IPCO and the ISC, have been shaping the public debate through their published reports and their engagement with civil society actors. The paper argues that oversight institutions are better equipped for shaping the democratic debate on bulk surveillance than any other societal actors due to their configuration of institutional features and statutory power. Empowering existing or creating new independent oversight entities with access to classified information and reliant on technical expertise is the way forward for democratic governance of intelligence services. [ABSTRACT FROM AUTHOR]

This paper compares multiple gridded data sets of daily UK precipitation to evaluate structural uncertainty in our reconstructions of historical rainfall. The data sets compared reflect two different sampling strategies and three different grid interpolation methods. In order to separate the influence of sampling and interpolation uncertainties, one of the data sets (produced by the Met Office) has been recreated using the sampling strategy of stations used in the European (E‐OBS) data set. The results confirm and build upon previous studies showing that relying on a relatively sparse but homogeneous network of stations limits the ability of the resulting data set to reliably estimate extreme rainfall at the daily timescale. It is shown that gridding methods that additionally make use of reference climatological data can avoid systematic bias in both the average and extreme events even when using a relatively sparse network of observations. This is an encouraging result in terms of our potential to reliably extend such data sets further back in time where the availability of digitized data is substantially lower than the more modern era. This paper compares multiple gridded rainfall data sets for the UK to analyse structural uncertainty in historical reconstructions of rainfall. In particular, as well as highlighting the shortcomings of using a sparse network of long‐running rainfall stations (as per E‐OBS), this paper shows that gridding methods that make use of reference climatological data help avoid systematic bias. This is a promising and valuable result for purposes of extending rainfall series back in time. [ABSTRACT FROM AUTHOR]

This paper presents the first criminological analysis of an online social reaction to a crime event of national significance, in particular the detection and propagation of cyberhate on social media following a terrorist attack. We take the Woolwich, London terrorist attack in 2013 as our event of interest and draw on Cohen's process of warning, impact, inventory and reaction to delineate a sequence of incidents that come to constitute a series of deviant responses following the attack. This paper adds to contemporary debates in criminology and the study of hate crime in three ways: (1) it provides the first analysis of the escalation, duration, diffusion and de-escalation of cyberhate in social media following a terrorist event; (2) it applies Cohen's work on action, reaction and amplification and the role of the traditional media to the online context and (3) it introduces and provides a case study in 'computational criminology'. [ABSTRACT FROM AUTHOR]

Objective: Atrial fibrillation (AF) is the most common cardiac arrhythmia, with an estimated prevalence of around 1.6% in the adult population. The analysis of the electrocardiogram (ECG) data acquired in the UK Biobank represents an opportunity to screen for AF in a large sub-population in the UK. The main objective of this paper is to assess ten machine-learning methods for automated detection of subjects with AF in the UK Biobank dataset., Approach: Six classical machine-learning methods based on support vector machines are proposed and compared with state-of-the-art techniques (including a deep-learning algorithm), and finally a combination of a classical machine-learning and deep learning approaches. Evaluation is carried out on a subset of the UK Biobank dataset, manually annotated by human experts., Main Results: The combined classical machine-learning and deep learning method achieved an F1 score of 84.8% on the test subset, and a Cohen's kappa coefficient of 0.83, which is similar to the inter-observer agreement of two human experts., Significance: The level of performance indicates that the automated detection of AF in patients whose data have been stored in a large database, such as the UK Biobank, is possible. Such automated identification of AF patients would enable further investigations aimed at identifying the different phenotypes associated with AF.

In the era of Big Data, the Internet has become one of the main data sources: Data can be collected for relatively low costs and can be used for a wide range of purposes. To be able to timely support solid decisions in any field, it is essential to increase data production efficiency, data accuracy, and reliability. In this framework, our paper aims at identifying an optimized and flexible method to collect and, at the same time, geolocate social media information over a whole country. In particular, the target of this paper is to compare three alternative methods to collect data from the social media Twitter. This is achieved considering four main comparison criteria: Collection time, dataset size, pre-processing phase load, and geographic distribution. Our findings regarding Great Britain identify one of these methods as the best option, since it is able to collect both the highest number of tweets per hour and the highest percentage of unique tweets per hour. Furthermore, this method reduces the computational effort needed to pre-process the collected tweets (e.g., showing the lowest collection times and the lowest number of duplicates within the geographical areas) and enhances the territorial coverage (if compared to the population distribution). At the same time, the effort required to set up this method is feasible and less prone to the arbitrary decisions of the researcher. [ABSTRACT FROM AUTHOR]

The UK Biobank (UKB) is a health research resource of major international importance, incorporating comprehensive characterization of >500 000 men and women recruited between 2006 and 2010 from across the UK. There is prospective tracking of health outcomes for all participants through linkages with national cohorts (death registers, cancer registers, electronic hospital records, and primary care records). The dataset has been enhanced with the UKB imaging study, which aims to scan a subset of 100 000 participants. The imaging protocol includes magnetic resonance imaging of the brain, heart, and abdomen, carotid ultrasound, and whole-body dual X-ray absorptiometry. Since its launch in 2015, over 48 000 participants have completed the imaging study with scheduled completion in 2023. Repeat imaging of 10 000 participants has been approved and commenced in 2019. The cardiovascular magnetic resonance (CMR) scan provides detailed assessment of cardiac structure and function comprising bright blood anatomic assessment (sagittal, coronal, and axial), left and right ventricular cine images (long and short axes), myocardial tagging, native T1 mapping, aortic flow, and imaging of the thoracic aorta. The UKB is an open access resource available to health researchers across all scientific disciplines from both academia and industry with no preferential access or exclusivity. In this paper, we consider how we may best utilize the UKB CMR data to advance cardiovascular research and review notable achievements to date. [ABSTRACT FROM AUTHOR]

To understand the links between Big Data and economic development is to focus on the knowledge that may be created from Big Data and the knowledge workers who can produce and use this knowledge to maximum economic impact. Using location quotients, this paper finds that the current geographical concentration of employees with skills to generate value from Big Data means that economic opportunities will be centred in the London and South East regions. In contrast, Big Data opportunities will be less important for the already lagging regions in Great Britain. [ABSTRACT FROM AUTHOR]

Due to the increased interest in micropollutants, this paper aims at quantifying and analyzing the UK online interest in Diclofenac, Estradiol, Azithromycin, Clarithromycin, and Erythromycin, substances included in the EU watchlist for monitoring, in order to examine if the public's online behavior and the use of these substances, in terms of issued prescriptions, are correlated. Using time series data from Google Trends from January 2004 to December 2014, an analysis of these substances in the UK, and in each UK region, i.e., England, Wales, Scotland, and Northern Ireland, is at first performed, followed by an analysis of interest by substance. The results show high interest in Diclofenac with a slight decline, while the Macrolides are significantly less popular though increasing. For Estradiol, the interest is low and declining throughout the examined period, in contrast to the scientific community, where Estradiol is the most studied substance. Prescription items and Google hits are highly correlated in the UK for Diclofenac, Azithromycin, and Clarithromycin, while no correlation is observed for Estradiol. Results from this study indicated that online search traffic data can be valuable in examining the public's online behavior towards the monitored micropollutants, and could assist with the evaluation and forecasting of their concentrations in the waste, surface, and ground water in the UK. [ABSTRACT FROM AUTHOR]

This paper proposes a novel multi-resolution clustering (MRC) method that for the first time classifies end customers directly from massive, volatile and uncertain smart metering data. It will firstly extract spectral features of load profiles by multi-resolution analysis (MRA), and then cluster and classify these features in the spectral-domain instead of time-domain. The key advantage is that the proposed method will allow a dynamic load profiling to be flexibly re-constructed from each spectral level. MRC addresses three key limitations in time-series based load profiling: i) large sample size: sample size is reduced by a novel two-stage clustering, which firstly clusters each customers' massive daily profiles into several Gaussian mixture models (GMMs) and then clusters all GMMs; ii) volatility: it avoids the interferences between different load features (e.g. magnitude, overall trend, spikes) by decomposing them onto different resolution levels, and then clustering separately; iii) uncertainties: as the GMM can give a probabilistic cluster membership instead of a deterministic one, an additive classification model based on the posterior probability is proposed to reflect the uncertainty between days. The proposed method is implemented on 6369 smart metered customers from Ireland, and compared with the load profiles used by the U.K. industry and traditional K-means clustering. The results show that the developed MRC outperformed the traditional methods in its ability in profiling load for big, volatile and uncertain smart metering data. [ABSTRACT FROM PUBLISHER]

Background: Data-intensive research in medicine and healthcare such as health-related big data research (HBDR) implies that data from clinical routine, research and patient-reported data, but also non-medical social or demographic data, are aggregated and linked in order to optimize biomedical research. In this context, notions of patient participation and involvement are frequently invoked to legitimize this kind of research and improve its governance. The aim of this debate paper is to critically examine the specific use and ethical role of participatory concepts in the context of HBDR and data-intensive research in medicine and healthcare., Discussion: We introduce basic conceptual distinctions for the understanding of participation by looking at relevant fields of application in politics, bioethics and medical research. Against this backdrop, we identify three paradigmatic participatory roles that patients/subjects are assigned within the field of HBDR: participants as providers of biomaterials and data, participants as administrators of their own research participation and participants as (co-)principal investigators. We further illustrate these roles by exemplary data-intensive research-initiatives. Our analysis of these initiatives and their respective participatory promises reveals specific ethical and practical shortcomings and challenges. Central problems affecting, amongst others, ethical and methodological research standards, as well as public trust in research, result from the negligence of essential political-ethical dimensions of genuine participation., Conclusions: Based on the conceptual distinctions introduced, we formulate basic criteria for justified appeals to participatory approaches in HBDR and data-intensive research in medicine and healthcare in order to overcome these shortcomings. As we suggest, this is not only a matter of conceptual clarity, but a crucial requirement for maintaining ethical standards and trust in HBDR and related medical research.

This paper reviews some of the challenges posed by the huge growth of experimental data generated by the new generation of large-scale experiments at UK national facilities at the Rutherford Appleton Laboratory (RAL) site at Harwell near Oxford. Such 'Big Scientific Data' comes from the Diamond Light Source and Electron Microscopy Facilities, the ISIS Neutron and Muon Facility and the UK's Central Laser Facility. Increasingly, scientists are now required to use advanced machine learning and other AI technologies both to automate parts of the data pipeline and to help find new scientific discoveries in the analysis of their data. For commercially important applications, such as object recognition, natural language processing and automatic translation, deep learning has made dramatic breakthroughs. Google's DeepMind has now used the deep learning technology to develop their AlphaFold tool to make predictions for protein folding. Remarkably, it has been able to achieve some spectacular results for this specific scientific problem. Can deep learning be similarly transformative for other scientific problems? After a brief review of some initial applications of machine learning at the RAL, we focus on challenges and opportunities for AI in advancing materials science. Finally, we discuss the importance of developing some realistic machine learning benchmarks using Big Scientific Data coming from several different scientific domains. We conclude with some initial examples of our 'scientific machine learning' benchmark suite and of the research challenges these benchmarks will enable. [ABSTRACT FROM AUTHOR]

Haplotype estimation, or phasing, has gained significant traction in large-scale projects due to its valuable contributions to population genetics, variant analysis, and the creation of reference panels for imputation and phasing of new samples. To scale with the growing number of samples, haplotype estimation methods designed for population scale rely on highly optimized statistical models to phase genotype data, and usually ignore read-level information. Statistical methods excel in resolving common variants, however, they still struggle at rare variants due to the lack of statistical information. In this study we introduce SAPPHIRE, a new method that leverages whole-genome sequencing data to enhance the precision of haplotype calls produced by statistical phasing. SAPPHIRE achieves this by refining haplotype estimates through the realignment of sequencing reads, particularly targeting low-confidence phase calls. Our findings demonstrate that SAPPHIRE significantly enhances the accuracy of haplotypes obtained from state of the art methods and also provides the subset of phase calls that are validated by sequencing reads. Finally, we show that our method scales to large data sets by its successful application to the extensive 3.6 Petabytes of sequencing data of the last UK Biobank 200,031 sample release. Author summary: Haplotype estimation, also known as phasing, is now applied to population scale projects, typically of hundreds of thousands of samples to millions of samples. Generally phasing relies on statistical methods as they provide very accurate results for common variations. However, for rare and very rare variants the lack of statistical power often results in poor phasing. The large amount of rare variations discovered with whole-genome sequencing as well as the number of samples makes it expensive to process. We have developed the SAPPHIRE method that leverages whole-genome sequencing data to verify and correct the phase at poorly phased variant loci. It does so by finding sequencing reads that contain both the poorly phased variant and an accurately phased common variant. SAPPHIRE scales with large data sets by specifically targeting variation where statistical phasing performed poorly, therefore it reduces the quantity of sequencing data to be processed and combines the advantages of both read-based and statistical approaches. We show the efficiency of SAPPHIRE by improving the estimated haplotypes for 200,031 samples in the UK Biobank. SAPPHIRE is free and available as open-source software. [ABSTRACT FROM AUTHOR]

This paper looks at some of the ethical challenges that Big Data and data linking present for official statistics, reviews some of the international initiatives in train, focusing on recent developments in the UK. It emphasises the importance of confidentiality in maintaining trust in official statistics, arguing that, although the ethical issues are everywhere acknowledged as important, the debate on this is still at an early stage, and needs to be pursued. [ABSTRACT FROM AUTHOR]

Global consumer lending has seen a compound annual growth rate (CAGR) of 4.8 per cent forecasted to 2020. The financial system is once again at risk; it is a decade since the credit crunch, yet the causes have not been solved; however, globally, the outstanding amount of credit doubled compared to the lending volume of 2008. Also, increasingly more credit decisions are being taken today. Furthermore, millennials' service expectations drive transformation from traditional lending into digital lending. The CAGR for digital lending is 53 per cent until 2025. Therefore, in this growing information age, new methods for credit risk scoring could form the central pillar for the continuity of a financial institution and the stability of the global financial system. This paper contains research from across the UK and the Netherlands: two advanced lending markets, selected because of their advancements in digital lending, to examine to what extent lenders can advance their credit decisions with individual risk assessments with artificial intelligence (AI). The research has applied supervised learning and has been performed on 133,152 mortgage and credit card customers in prime, near prime and sub-prime lending segments of three European lenders across the UK and the Netherlands during the period January 2016 to July 2017. As candidate models, we chose neural nets and random forests, as they are the most popular supervised learning methods in credit risk for their benefit of applying both structured and unstructured data. The research describes three experiments that develop the AI probability of default models and compares the model quality with the quality of the traditional applied logistic probability of default (PD) models. In all experiments, AI models performed better than the traditional models. Scalable automated credit risk solutions can therefore build on AI in their risk scoring. [ABSTRACT FROM AUTHOR]

The ambient population, i.e. the demographics and volume of people in a particular location throughout the day, has been studied less than the night-time residential population. Although the spatio-temporal behaviour of some groups, such as commuters, are captured in sources such as population censuses, much less is known about groups such as retired people who have less documented behaviour patterns. This paper uses agent-based modelling to disaggregate some ambient population data to estimate the size and demographics of the constituent populations during the day. This is accomplished by first building a model of commuters to model typical 9–5 workday patterns. The differences between the model outputs and real footfall data (the error) can be an indication of the contributions that other groups make to the overall footfall. The research then iteratively simulates a wider range of demographic groups, maximising the correspondence between the model and data at each stage. An application of this methodology to the town centre of Otley, West Yorkshire, UK, is presented. Ultimately this approach could lead to a better understanding about how town- and city-centres are used by residents and visitors, contributing useful information in a situation where raw data on the populations do not exist. [ABSTRACT FROM AUTHOR]

Highlights • The paper presents a verification of HDM-4 fuel consumption estimates by comparing these to real world measurements from a large dataset from a truck telematic database. • Results of the study show that the latest calibration of HDM-4 performed in UK is not able to estimate the fuel consumption of the considered fleet of trucks reliably. • The authors suggest that, in order to use HDM-4 at a strategic level in road asset management, a full recalibration of the model should be performed in UK. • Results show also that analysis of the 'big data' available in the telematic database of fleet managers can help in updating HDM-4 without performing new experiments and can represent a valid alternative to the traditional approach. Abstract This paper presents an assessment of the accuracy of the HDM-4 fuel consumption model calibrated for the United Kingdom and evaluates the need for further calibration of the model. The study focuses on HGVs and compares estimates made by HDM-4 to measurements from a large fleet of vehicles driving on motorways in England. The data was obtained from the telematic database of truck fleet managers (SAE J1939) and includes three types of HGVs: light, medium and heavy trucks. Some 19,991 records from 1645 trucks are available in total. These represent records of trucks driving at constant speed along part of the M1 and the M18, two motorways in England. These conditions have been simulated in HDM-4 by computing fuel consumption for each truck type driving at a constant speed of 85 km/h on a flat and straight road segment in good condition. Estimates are compared to real measurements under two separate sets of assumptions. First, the HDM-4 model calibrated for the UK has been used. Then, the model was updated to take into account vehicle weight and frontal area specific to the considered vehicles. The paper shows that the current calibration of HDM-4 for the United Kingdom already requires recalibration. The quality of the model estimates can be improved significantly by updating vehicle weight and frontal area in HDM-4. The use of HGV fleet and network condition data as described in this paper provides an opportunity to verify HDM-4 continuously. [ABSTRACT FROM AUTHOR]

This paper proposes an innovative statistical matching method to combine the advantages of large national surveys and time diary data. We use data from two UK datasets that share stylised time-use information, crucial for the matching process. In particular, time-diary information of an individual from the Home On-line Study, our donor data set, is imputed to a similar individual from the British Household Panel Survey, our recipient dataset. Propensity score methods are used in conjunction with Mahalanobis matching to increase matching quality. [ABSTRACT FROM AUTHOR]

This paper details an innovative approach which enables the analysis of small area population change across four decades. Population surfaces are generated using small area data (enumeration districts or output areas) for each Census from 1971 to 2011 inclusive. The paper details the methods used in the creation of these surfaces, and discusses the rationale behind this approach, arguing that grids represent the most appropriate model for assessing population distributions. Methods for grid creation are tested using pre-existing population grids for Northern Ireland as a benchmark. The method developed is then applied to create population grids for the rest of the UK for 1971, 1981, 1991, 2001 and 2011. The changing population structures of small areas across these five time points are explored here to illustrate the value of this approach. The publically-available data resource – the final product of the ‘ PopChange ’ project – will facilitate exploration of long-term changes in populations over small areas. The paper argues that maximum advantage could be taken of the ‘big data revolution’ if such data were gridded in a similar way, allowing them to be placed in a longer-term historical context, using tools made available through the PopChange project. [ABSTRACT FROM AUTHOR]

Background: The prevalence of depression among people with chronic pain remains unclear due to the heterogeneity of study samples and definitions of depression. We aimed to identify sources of variation in the prevalence of depression among people with chronic pain and generate clinical prediction models to estimate the probability of depression among individuals with chronic pain. Methods: Participants were from the UK Biobank. The primary outcome was a "lifetime" history of depression. The model's performance was evaluated using discrimination (optimism-corrected C statistic) and calibration (calibration plot). Results: Analyses included 24,405 patients with chronic pain (mean age 64.1 years). Among participants with chronic widespread pain, the prevalence of having a "lifetime" history of depression was 45.7% and varied (25.0–66.7%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.66; good calibration on the calibration plot) included age, BMI, smoking status, physical activity, socioeconomic status, gender, history of asthma, history of heart failure, and history of peripheral artery disease. Among participants with chronic regional pain, the prevalence of having a "lifetime" history of depression was 30.2% and varied (21.4–70.6%) depending on patient characteristics. The final clinical prediction model (optimism-corrected C statistic: 0.65; good calibration on the calibration plot) included age, gender, nature of pain, smoking status, regular opioid use, history of asthma, pain location that bothers you most, and BMI. Conclusions: There was substantial variability in the prevalence of depression among patients with chronic pain. Clinically relevant factors were selected to develop prediction models. Clinicians can use these models to assess patients' treatment needs. These predictors are convenient to collect during daily practice, making it easy for busy clinicians to use them. [ABSTRACT FROM AUTHOR]

• Analyse the key risk factors influencing cargo theft from freight supply chains. • Develop a data-driven Bayesian Network model to realise cargo theft risk prediction and diagnosis. • Evaluate the critical risk factors to predict the occurrence of cargo theft accidents. • Analyse the real accidents to verify the model and provide implications for cargo theft prevention. Cargo theft has been among the most concerning risks influencing global freight supply chains, which causes serious supply chain disruptions, injuries/deaths, economic loss, and environmental damage. However, there are very few studies on the risk analysis of cargo theft, particularly in a quantitative manner, and fewer on the relevant risk factors affecting theft-related accidents in the current literature. This paper aims to analyse the risk influential factors (RIFs) of cargo theft and predict the occurrence likelihood of different types of cargo theft accidents. The historical data of 9316 cargo theft accidents that happened in the UK from 2009 to 2021 were first collected from the TAPA IIS database, and then purified and trained to construct a Bayesian network (BN) based cargo theft risk analysis model. The data-driven BN interprets the interdependency of RIFs and their combined effects on the occurrence of different types of cargo theft accidents. Compared with the previous studies, this paper makes new contributions, including that (1) The cargo theft RIFs are identified from the literature and accident records. (2) A data-driven BN is proposed to construct the model with uncertainty to realise cargo theft risk prediction and diagnosis. (3) The critical RIFs contributing to cargo theft are evaluated and prioritised to predict the occurrence of possible cargo theft accidents. (4) The real accidents are investigated to verify the model and draw useful insights for cargo theft prevention. The findings show that the most influential RIFs for the occurrence of cargo theft accidents are product category, year, location type, modus operandi (MO), and region. The findings also reveal the combined risk contributions of the RIFs, hence providing useful insights for cost-effective theft risk control in practice. [ABSTRACT FROM AUTHOR]

This paper provides doubly robust estimators for treatment effect parameters which are defined in a multivalued treatment effect framework. We apply this method to the unique dataset of the 1970 British Cohort Study (BCS70) to estimate returns to various levels of schooling. The analysis is carried out for female and male samples separately to capture possible gender differences. Average returns are estimated for the entire population, as well as conditional on having a specific educational achievement. For males, relative to no qualification, we find an average return to O-levels of 6.3%, to A-levels of 7.9% and to higher education of 25.4%. The estimated average returns to O-level and A-level relative to no qualification are insignificant for females, whereas the return to higher education is 19.9%.Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The layman's answer to the question posted in the title to this paper lies in the question itself. The common understanding of people when they talk about information about themselves is that it is indeed "theirs". Until relatively recently, the law has been content to remain agnostic on the subject. The Common Law in general and English Courts in particular have traditionally avoided philosophical debates about the nature of things, preferring to develop concepts and principles from the results of cases decided on specific facts and circumstances. This approach has been acceptable while we have been winding our way gently up the foothills of the Information Age, but now that we see the towering peak of Big Data standing before us, covered by the ubiquitous Cloud, it is necessary to make a critical examination of some of the basic assumptions which we have hitherto carried with us about the way in which the law should treat rights over personal information. This paper will argue that the correct approach which the law should adopt is a proprietary one. That is to say that the protection of the economic value inherent in personal information should be grounded in property rights acknowledged by the law. [ABSTRACT FROM AUTHOR]

This article contributes to the international comparative analysis of university venture capital (UVC), providing a quasi-experimental design for follow-up research and practice. The US venture capital industry, with its unicorn focused high-growth format opened up a venture capital gap. UVC transmutes academic innovation into high-tech firms, industries and regional renewal, filling interstitial funding gaps among angel, public and private venture capital offers. It is a knowledge-based industrial policy by Another Name, with direct/explicit and indirect/implicit versions, on a continuum with variation depending upon shifting ideological and competitive concerns. Beyond as of right "womb" provision, UVC capstones an academic innovation ecosystem of technology transfer, incubation and acceleration, translational research, proof of concept funds and entrepreneurship education. Venture capital, exemplified by Sand Hill Road, de-emphasizes classic regional development objectives, neglecting appropriability conditions such as academic and regional circumstances that UK and China prioritize. More modest firm formation outcomes are dismissed as failures, with entrepreneurs encouraged to return to the entrepreneurial churn. We examine the origin and development of UVC from macro, meso and micro, historical and comparative perspectives. Multi-method/multi-sample, comparative case study, and big data analytics show the constraint, variety, and early affinity of UVC to academic icons with significant untapped potential to inspire widespread economic and social advance. [ABSTRACT FROM AUTHOR]

Network analysis provides a rich framework to model complex phenomena, such as human brain connectivity. It has proven efficient to understand their natural properties and design predictive models. In this paper, we study the variability within groups of networks, i.e., the structure of connection similarities and differences across a set of networks. We propose a statistical framework to model these variations based on manifold-valued latent factors. Each network adjacency matrix is decomposed as a weighted sum of matrix patterns with rank one. Each pattern is described as a random perturbation of a dictionary element. As a hierarchical statistical model, it enables the analysis of heterogeneous populations of adjacency matrices using mixtures. Our framework can also be used to infer the weight of missing edges. We estimate the parameters of the model using an Expectation-Maximization-based algorithm. Experimenting on synthetic data, we show that the algorithm is able to accurately estimate the latent structure in both low and high dimensions. We apply our model on a large data set of functional brain connectivity matrices from the UK Biobank. Our results suggest that the proposed model accurately describes the complex variability in the data set with a small number of degrees of freedom. [ABSTRACT FROM AUTHOR]

This study explores the nexus between digital and green transformations—the so-called "twin" transition—in European regions in an effort to identify the impact of digital and environmental technologies on the greenhouse gas (GHG) emissions originating from industrial production. We conduct an empirical analysis based on an original dataset that combines information on environmental and digital patent applications with information on GHG emissions from highly polluting plants for the period 2007–2016 at the metropolitan region level in the European Union and the UK. Results show that the local development of environmental technologies reduces GHG emissions, while the local development of digital technologies increases them, albeit in the latter case different technologies seem to have different impacts on the environment, with big data and computing infrastructures being the most detrimental. We also find differential impacts across regions depending on local endowment levels of the respective technologies: the beneficial effect of environmental technologies is stronger in regions with large digital technology endowments and, conversely, the detrimental effect of digital technologies is weaker in regions with large green technology endowments. Policy actions promoting the "twin" transition should take this evidence into account, in light of the potential downside of the digital transformation when not combined with the green transformation. [ABSTRACT FROM AUTHOR]

Lagrangian particle dispersion models (LPDMs) have been used extensively to calculate source-receptor relationships ("footprints") for use in applications such as greenhouse gas (GHG) flux inversions. Because a single model simulation is required for each data point, LPDMs do not scale well to applications with large data sets such as flux inversions using satellite observations. Here, we develop a proof-of-concept machine learning emulator for LPDM footprints over a ∼ 350 km × 230 km region around an observation point, and test it for a range of in situ measurement sites from around the world. As opposed to previous approaches to footprint approximation, it does not require the interpolation or smoothing of footprints produced by the LPDM. Instead, the footprint is emulated entirely from meteorological inputs. This is achieved by independently emulating the footprint magnitude at each grid cell in the domain using gradient-boosted regression trees with a selection of meteorological variables as inputs. The emulator is trained based on footprints from the UK Met Office's Numerical Atmospheric-dispersion Modelling Environment (NAME) for 2014 and 2015, and the emulated footprints are evaluated against hourly NAME output from 2016 and 2020. When compared to CH 4 concentration time series generated by NAME, we show that our emulator achieves a mean R -squared score of 0.69 across all sites investigated between 2016 and 2020. The emulator can predict a footprint in around 10 ms, compared to around 10 min for the 3D simulator. This simple and interpretable proof-of-concept emulator demonstrates the potential of machine learning for LPDM emulation. [ABSTRACT FROM AUTHOR]

While official statistics provide lagged and aggregate information on the housing market, extensive information is available publicly on real-estate websites. By web-scraping them for the UK on a daily basis, this paper extracts a large database from which we build timely and highly granular indicators. One originality of the dataset is to focus on the supply side of the housing market, allowing to compute innovative indicators reflecting the sellers' perspective such as the number of new listings posted or how prices fluctuate over time for existing listings. Matching listing prices in our dataset with transacted prices from the notarial database, using machine learning, also measures the negotiation margin of buyers. During the Covid-19 crisis, these indicators demonstrate the freezing of the market and the "wait-and-see" behaviour of sellers. They also show that listing prices after the lockdown experienced a continued decline in London but increased in other regions. [ABSTRACT FROM AUTHOR]

Genomic regions under positive selection harbor variation linked for example to adaptation. Most tools for detecting positively selected variants have computational resource requirements rendering them impractical on population genomic datasets with hundreds of thousands of individuals or more. We have developed and implemented an efficient haplotype-based approach able to scan large datasets and accurately detect positive selection. We achieve this by combining a pattern matching approach based on the positional Burrows–Wheeler transform with model-based inference which only requires the evaluation of closed-form expressions. We evaluate our approach with simulations, and find it to be both sensitive and specific. The computational resource requirements quantified using UK Biobank data indicate that our implementation is scalable to population genomic datasets with millions of individuals. Our approach may serve as an algorithmic blueprint for the era of "big data" genomics: a combinatorial core coupled with statistical inference in closed form. [ABSTRACT FROM AUTHOR]

Financial transactions are increasingly used by consumer apps and financial service providers to estimate consumption-based carbon emissions. This approach promises a low-resource, ultra-fast, and highly scalable approach to measuring emissions at different levels of potential policy intervention--spanning the national, subnational, local, and individual level. Despite this potential, there is a lack of research exploring the validity of this approach to carbon profiling. Here we address this oversight in three ways. First, we provide a step-by-step description of our approach toward estimating carbon footprints from micro-level transaction data generated by more than 100,000 customers of a large retail bank in theUnitedKingdom. Second, we quantitatively compare emission estimates obtained from transaction data with those calculated from a more standard data source used in carbon profiling, the largest household expenditure survey in the United Kingdom. Third, we offer a detailed qualitative comparison of the advantages and disadvantages of transactions versus alternative data sources (such as survey data), across key dimensions including data availability, data quality, and data detail. We find that financial transactions offer a credible alternative to survey-based sources and, if made more widely accessible, could provide important advantages for profiling emissions. These include objective, micro-level data on consumption behaviors, larger sample sizes, and longitudinal, frequent data capture. [ABSTRACT FROM AUTHOR]

This study draws on organizational learning and strategic decision-making theory to develop a conceptual framework to explore how the selection measures of BDA systems and external support partners are linked to BDA system quality, and how these influence firms' competitive position. Through a cross-sectional survey of 523 IT professionals from the US, UK, and India, using path analysis and structural equation modeling, we found that the information systems selection process, enhanced by knowledge management capabilities, is positively related to the BDA system quality and firms' performance. However, inconsistent with prior studies on transactional systems, we found no support for the hypothesis that software vendor criteria influence BDA quality. Also, in selecting systems and external facilitators, organizations appear to be pivoting towards parameters that are considered "emerging", such as cloud computing, DevOps, and agile experiences, as they increase the likelihood of unlocking business value from BDA. [ABSTRACT FROM AUTHOR]

Objective: Atrial fibrillation (AF) is the most common cardiac arrhythmia, with an estimated prevalence of around 1.6% in the adult population. The analysis of the electrocardiogram (ECG) data acquired in the UK Biobank represents an opportunity to screen for AF in a large sub-population in the UK. The main objective of this paper is to assess ten machine-learning methods for automated detection of subjects with AF in the UK Biobank dataset. Approach: Six classical machine-learning methods based on support vector machines are proposed and compared with state-of-the-art techniques (including a deep-learning algorithm), and finally a combination of a classical machine-learning and deep learning approaches. Evaluation is carried out on a subset of the UK Biobank dataset, manually annotated by human experts. Main results: The combined classical machine-learning and deep learning method achieved an F1 score of 84.8% on the test subset, and a Cohen’s kappa coefficient of 0.83, which is similar to the inter-observer agreement of two human experts. Significance: The level of performance indicates that the automated detection of AF in patients whose data have been stored in a large database, such as the UK Biobank, is possible. Such automated identification of AF patients would enable further investigations aimed at identifying the different phenotypes associated with AF. [ABSTRACT FROM AUTHOR]

Our work addresses the influence of the growing adoption of information and communication technologies (ICT) for campaigning purposes on the evolving dynamics of information flows from the eminently social beings that candidates are. Our approach combines an analysis of contents to technological and methodological concerns. The breadth of these objectives as well as the amount of data to be considered pointed to a need for collaboration between several researchers for sharing out tasks and bringing together expertise from various disciplines. This paper presents results concerning three of the data collections life cycle phases: collection, cleaning, and storage. The result is a data collection ready to be analysed for different purposes. In particular, in our experimental validation it has been used for comparing political campaigns behaviour in France and the United Kingdom during the European elections in 2015. [ABSTRACT FROM AUTHOR]

The construction of intercity highways by the government has resulted in a progressive increase in vehicle emissions and pollution from noise, dust, and vibrations despite its recognition of the air pollution menace. Efforts that have targeted roadside pollution still do not accurately monitor deadly pollutants such as nitrogen oxides and particulate matter. Reports on regional highways across the country are based on a limited number of fixed monitoring stations that are sometimes located far from the highway. These periodic and coarse-grained measurements cause inefficient highway air quality reporting, leading to inaccurate air quality forecasts. This paper, therefore, proposes and validates a scalable deep learning framework for efficiently capturing fine-grained highway data and forecasting future concentration levels. Highways in four different UK regions - Newport, Lewisham, Southwark, and Chepstow were used as case studies to develop a REVIS system and validate the proposed framework. REVIS examined the framework's ability to capture granular pollution data, scale up its storage facility to rapid data growth and translate high-level user queries to structured query language (SQL) required for exploratory data analysis. Finally, the framework's suitability for predictive analytics was tested using fastai's library for tabular data, and automated hyperparameter tuning was implemented using bayesian optimisation. The results of our experiments demonstrate the suitability of the proposed framework in building end-to-end systems for extensive monitoring and forecasting of pollutant concentration levels on highways. The study serves as a background for future related research looking to improve the overall performance of roadside and highway air quality forecasting models. • The need for a scalable framework for Highway air quality monitoring is highlighted. • A deep learning framework for monitoring and forecasting concentration levels is proposed and validated. • Low-cost monitoring units are developed, evaluated, and deployed based on the framework's recommendations. • The framework's auto SQL generation capability and exploratory analysis are evaluated. • The strategies adopted in creating a meaningful validation set and developing forecasting models using Fastai are reported. [ABSTRACT FROM AUTHOR]

The recent advances in Internet of Things (IoT), computational analytics, processing power, and assimilation of Big Data (BD) are playing an important role in revolutionizing maintenance and operations regimes within the wider facilities management (FM) sector. The BD offers the potential for the FM to obtain valuable insights from a large amount of heterogeneous data collected through various sources and IoT allows for the integration of sensors. The aim of this article is to extend the exploratory studies conducted on Big Data analytics (BDA) implementation and empirically test and categorize the associated drivers and challenges. Using exploratory factor analysis (EFA), the researchers aim to bridge the current knowledge gap and highlight the principal factors affecting the BDA implementation. Questionnaires detailing 26 variables are sent to the FM organization in the U.K. who are in the process or have already implemented BDA initiatives within their FM operations. Fifty-two valid responses are analyzed by conducting EFA. The findings suggest that driven by market competition and ambitious sustainability goals, the industry is moving to holistically integrate analytics into its decision making. However, data quality, technological barriers, inadequate preparedness, data management, and governance issues and skill gaps are posing to be significant barriers to the fulfillment of expected opportunities. The findings of this study have important implications for FM businesses that are evaluating the potential of the BDA and IoT applications for their operations. Most importantly, it addresses the role of the BD maturity in FM organizations and its implications for perception of drivers. [ABSTRACT FROM AUTHOR]

The term political extremism is commonly used to refer to political attitudes considered to be outside the ideological mainstream. This study leverages computational content analysis of big data to longitudinally examine (1970–2019) the prevalence of terms denoting far-right and far-left political extremism in more than 30 million written news and opinion articles from 54 news media outlets popular in the United States and the United Kingdom. We find that the usage of terms denoting right and left political extremism has been increasing across news media outlets in both countries. This trend is particularly stark for far-right-denoting terms, which have been growing in prevalence since at least 2008. Most U.S. and U.K. news media outlets tend to use far-right-denoting terms substantially more often than they use far-left-denoting terms. The rising prevalence in news media of terms denoting political extremism is strongly correlated with similar growing usage of terms denoting prejudice and social justice discourse. [ABSTRACT FROM AUTHOR]

This article presents the first-ever big data study of the student evaluation of teaching (SET) using artificial intelligence (AI). We train natural language processing (NLP) models on 1.6 million student evaluations from the US and the UK. We address two research questions: (1) are these models able to predict student ratings from the student textual feedback, and (2) can AI-powered SET eliminate the problems of the traditional SET based on Likert scale surveys. We test these NLP models on a new dataset of 12,386 university reviews from the UK and on 155 SET reviews from a university that agreed to run a pilot AI project. The trained NLP models exhibited high prediction accuracy, and they learnt two biases from humans, those of extreme responding and assigning higher ratings to less demanding courses. In the future, universities will likely adopt many AI-based tools that have proved successful in client management in other sectors. However, our results make a strong case against using AI as a black box for performativity purposes. It should remain a useful tool for university administrators who are aware of the AI weaknesses documented here. [ABSTRACT FROM AUTHOR]