Search

This paper analyses employment transitions and workers' skills in Brazil using a random sample from the universe of formal labour contracts covering the period from 2003 to 2018. We develop a novel procedure to derive a measure of occupational distance and internationally comparable skill measures from occupations' task descriptions in the country under analysis based on machine learning and natural language processing methods, but without usual ad hoc classifications. Our findings confirm that workers who use non-routine cognitive skills intensively experience the highest employment growth rates and wages. Their labour market exit risk is relatively low, occupational and sectoral changes are least common and, in the case of occupational switching, non-routine cognitive workers tend to find occupations that are higher-paid and closer in terms of their task content. Against the same characteristics, routine and non-routine manual workers are worse off in the labour market. Overall, there have been signs of routine-biased technological change and employment polarization since the 2014 Brazilian economic crisis. [ABSTRACT FROM AUTHOR]

In this paper we study neural networks and their approximating power in panel data models. We provide asymptotic guarantees on deep feed-forward neural network estimation of the conditional mean, building on the work of Farrell et al. (2021), and explore latent patterns in the cross-section. We use the proposed estimators to forecast the progression of new COVID-19 cases across the G7 countries during the pandemic. We find significant forecasting gains over both linear panel and nonlinear time-series models. Containment or lockdown policies, as instigated at the national level by governments, are found to have out-of-sample predictive power for new COVID-19 cases. We illustrate how the use of partial derivatives can help open the "black box" of neural networks and facilitate semi-structural analysis: school and workplace closures are found to have been effective policies at restricting the progression of the pandemic across the G7 countries. But our methods illustrate significant heterogeneity and time variation in the effectiveness of specific containment policies. [ABSTRACT FROM AUTHOR]

Our study investigates the heterogeneity of skill demands within occupations, the firm activities that are associated with demand for broader skill sets, and the firm characteristics that are related to particular skills and different combinations of skills. We use a unique matched database of firm-level data and online job vacancy data for a developing economy, namely, India. Employing a multi-level machine learning technique and an innovative skill taxonomy, we identify and categorize skill requirements of firms. Our empirical analysis provides robust evidence of significant heterogeneity in skill requirements across firms within the same occupations. Additionally, we show that firms demanding diverse skills differ from their counterparts. Firms that are competitive in international markets, as well as those that are more innovative, require digital skills and specific combinations of digital and other skills. Our findings highlight the crucial role played by firms in defining the changing nature of work. [ABSTRACT FROM AUTHOR]

Semi-Supervised Learning (SSL) has been an effective way to leverage abundant unlabeled data with extremely scarce labeled data. However, most SSL methods are commonly based on instance-wise consistency between different data transformations. Therefore, the label guidance on labeled data is hard to be propagated to unlabeled data. Consequently, the learning process on labeled data is much faster than on unlabeled data which is likely to fall into a local minima that does not favor unlabeled data, leading to sub-optimal generalization performance. In this paper, we propose FlatMatch which minimizes a cross-sharpness measure to ensure consistent learning performance between the two datasets. Specifically, we increase the empirical risk on labeled data to obtain a worst-case model which is a failure case that needs to be enhanced. Then, by leveraging the richness of unlabeled data, we penalize the prediction difference (i.e., cross-sharpness) between the worst-case model and the original model so that the learning direction is beneficial to generalization on unlabeled data. Therefore, we can calibrate the learning process without being limited to insufficient label information. As a result, the mismatched learning performance can be mitigated, further enabling the effective exploitation of unlabeled data and improving SSL performance. Through comprehensive validation, we show FlatMatch achieves state-of-the-art results in many SSL settings., Comment: NeurIPS 2023

This study investigates the application of an artificial neural network framework for analysing water pollution caused by solids. Water pollution by suspended solids poses significant environmental and health risks. Traditional methods for assessing and predicting pollution levels are often time-consuming and resource-intensive. To address these challenges, we developed a model that leverages a comprehensive dataset of water quality from total suspended solids. A convolutional neural network was trained under a transfer learning approach using data corresponding to different total suspended solids concentrations, with the goal of accurately predicting low, medium and high pollution levels based on various input variables. Our model demonstrated high predictive accuracy, outperforming conventional statistical methods in terms of both speed and reliability. The results suggest that the artificial neural network framework can serve as an effective tool for real-time monitoring and management of water pollution, facilitating proactive decision-making and policy formulation. This approach not only enhances our understanding of pollution dynamics but also underscores the potential of machine learning techniques in environmental science., Comment: 42 pages, 8 figures and 2 tables

We assess whether online data on vacancies and applications to a job board are a suitable source for studying skills dynamics outside of Europe and the United States, where a rich literature has examined skills dynamics using online vacancy data. Yet, the knowledge on skills dynamics is scarce for other countries, irrespective of their level of development. We first propose a taxonomy that systematically aggregates three broad categories of skills - cognitive, socioemotional and manual - and fourteen commonly observed and recognizable skills sub-categories, which we define based on unique skills identified through keywords and expressions. Our aim is to develop a taxonomy that is comprehensive but succinct, suitable for the labour market realities of developing and emerging economies and adapted to online vacancies and applicants' data. Using machine-learning techniques, we then develop a methodology that allows implementing the skills taxonomy in online vacancy and applicants' data, thus capturing both the supply and the demand side. Implementing the methodology with Uruguayan data from the job board BuscoJobs, we assign skills to 64 per cent of applicants' employment spells and 94 per cent of vacancies. We consider this a successful implementation since the exploited text information often does not follow a standardized format. The advantage of our approach is its reliance on data that is currently available in many countries across the world, thereby allowing for country-specific analysis that does not need to assume that occupational skills bundles are the same across countries. To the best of our knowledge, we are the first to explore this approach in the context of emerging economies. [ABSTRACT FROM AUTHOR]

The Arithmetic Progression Graph Labeling is an NP-complete problem with various applications, including optimizing scheduling problems. This paper presents Quadratic Unconstrained Boolean Optimization (QUBO) solutions for the version with fixed vertex labels of this problem, then the original general problem. We use and compare standard (D-Wave Advantage and Advantage 2 Prototype) and hybrid (D-Wave Leap Hybrid Solver Service) methods to solve these problems with D-Wave quantum machines. Our experiments suggest that the hybrid methods outperform the standard ones. [ABSTRACT FROM AUTHOR]

Drug resistance is a major threat to the global health and a significant concern throughout the clinical treatment of diseases and drug development. The mutation in proteins that is related to drug binding is a common cause for adaptive drug resistance. Therefore, quantitative estimations of how mutations would affect the interaction between a drug and the target protein would be of vital significance for the drug development and the clinical practice. Computational methods that rely on molecular dynamics simulations, Rosetta protocols, as well as machine learning methods have been proven to be capable of predicting ligand affinity changes upon protein mutation. However, the severely limited sample size and heavy noise induced overfitting and generalization issues have impeded wide adoption of machine learning for studying drug resistance. In this paper, we propose a robust machine learning method, termed SPLDExtraTrees, which can accurately predict ligand binding affinity changes upon protein mutation and identify resistance-causing mutations. Especially, the proposed method ranks training data following a specific scheme that starts with easy-to-learn samples and gradually incorporates harder and diverse samples into the training, and then iterates between sample weight recalculations and model updates. In addition, we calculate additional physics-based structural features to provide the machine learning model with the valuable domain knowledge on proteins for this data-limited predictive tasks. The experiments substantiate the capability of the proposed method for predicting kinase inhibitor resistance under three scenarios, and achieves predictive accuracy comparable to that of molecular dynamics and Rosetta methods with much less computational costs., Comment: 14 pages, 5 figures

Copyright of Working Papers (Croatian National Bank) is the property of Croatian National Bank and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of OECD Statistics Working Papers is the property of Organisation for Economic Cooperation & Development and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Rising interest rates and structural shifts in the demand for space have strained CRE markets and prompted concern about contagion to the largest CRE debt holder: banks. We use confidential loan-level data on bank CRE portfolios to examine banks' exposure to at-risk CRE loans. We investigate (1) what loan characteristics are associated with delinquency and (2) to what extent the portfolio composition of major CRE lenders determines their exposure to losses. Higher LTVs, larger property sizes, and greater local remote work tendencies are all associated with increased delinquency risk, particularly for office loans. We use several machine learning algorithms to demonstrate that variation in exposure to these risk factors can account for most of the performance disparity across different types of CRE lenders. The headline result is that small banks' comparatively modest delinquency rates mostly reflect observable portfolio characteristics--predominantly their low holdings of large-sized office loans--rather than unobserved factors like extension or modification tendencies. [ABSTRACT FROM AUTHOR]

Despite growing interest in the use of complex models, such as machine learning (ML) models, for credit underwriting, ML models are difficult to interpret, and it is possible for them to learn relationships that yield de facto discrimination. How can we understand the behavior and potential biases of these models, especially if our access to the underlying model is limited? We argue that counterfactual reasoning is ideal for interpreting model behavior, and that Gaussian processes (GP) can provide approximate counterfactual reasoning while also incorporating uncertainty in the underlying model's functional form. We illustrate with an exercise in which a simulated lender uses a biased machine model to decide credit terms. Comparing aggregate outcomes does not clearly reveal bias, but with a GP model we can estimate individual counterfactual outcomes. This approach can detect the bias in the lending model even when only a relatively small sample is available. To demonstrate the value of this approach for the more general task of model interpretability, we also show how the GP model's estimates can be aggregated to recreate the partial density functions for the lending model. [ABSTRACT FROM AUTHOR]

Machine learning and artificial intelligence methods are often referred to as \black boxes" when compared to traditional regression-based approaches. However both traditional and machine learning methods are concerned with modeling the joint distribution between endogenous (target) and exogenous (input) variables. The fitted models are themselves functionals of the data, about which we can do statistical inference using computationally intensive methods such as the bootstrap. Where linear models describe the fitted relationship between the target and input variables via the slope of that relationship (coeffcient estimates), the same fitted relationship can be described rigorously for any machine learning model by first-differencing the partial dependence functions. Bootstrapping these first-differenced functionals provides standard errors and confidence intervals for the estimated relationships. We show that this approach replicates the point estimates of coeffcients attained in a linear OLS models, and demonstrate how this generalizes to marginal relationships in ML/AI models. This paper extends the partial dependence plot described in Friedman (2001), and visualizes the marginal distribution used to construct the PDP as described in Goldstein et al. (2015) before applying the steps described above. We further discuss the extension of PDP into a Shapley value decomposition and explore how it can be used to further explain model outputs. We conclude with a hedonic house pricing example, which illustrates how machine learning methods such as random forests, deep neural net, and support vector regression automatically capture nonlinearities and shed light on inconsistencies revealed by meta-studies of hedonic house pricing. [ABSTRACT FROM AUTHOR]

David Hendry has made--and continues to make--pivotal contributions to the econometrics of empirical economic modeling, economic forecasting, econometrics software, substantive empirical economic model design, and economic policy. This paper reviews his contributions by topic, emphasizing the overlaps between different strands in his research and the importance of real-world problems in motivating that research. [ABSTRACT FROM AUTHOR]

Most consistent estimators are what Müller (2007) terms “highly fragile”: prone to total breakdown in the presence of a handful of unusual data points. This compromises inference. Robust estimation is a (seldom-used) solution, but commonly used methods have drawbacks. In this paper, building on methods that are relatively unknown in economics, we provide a new tool for robust estimates of mean and covariance, useful both for robust estimation and for detection of unusual data points. It is relatively fast and useful for large data sets. Our performance testing indicates that our baseline method performs on par with, or better than, two of the currently best available methods, and that it works well on benchmark data sets. We also demonstrate that the issues we discuss are not merely hypothetical, by re-examining a prominent economic study and demonstrating its central results are driven by a set of unusual points. [ABSTRACT FROM AUTHOR]

Deep neural networks achieve remarkable performances on a wide range of tasks with the aid of large-scale labeled datasets. Yet these datasets are time-consuming and labor-exhaustive to obtain on realistic tasks. To mitigate the requirement for labeled data, self-training is widely used in semi-supervised learning by iteratively assigning pseudo labels to unlabeled samples. Despite its popularity, self-training is well-believed to be unreliable and often leads to training instability. Our experimental studies further reveal that the bias in semi-supervised learning arises from both the problem itself and the inappropriate training with potentially incorrect pseudo labels, which accumulates the error in the iterative self-training process. To reduce the above bias, we propose Debiased Self-Training (DST). First, the generation and utilization of pseudo labels are decoupled by two parameter-independent classifier heads to avoid direct error accumulation. Second, we estimate the worst case of self-training bias, where the pseudo labeling function is accurate on labeled samples, yet makes as many mistakes as possible on unlabeled samples. We then adversarially optimize the representations to improve the quality of pseudo labels by avoiding the worst case. Extensive experiments justify that DST achieves an average improvement of 6.3% against state-of-the-art methods on standard semi-supervised learning benchmark datasets and 18.9%$ against FixMatch on 13 diverse tasks. Furthermore, DST can be seamlessly adapted to other self-training methods and help stabilize their training and balance performance across classes in both cases of training from scratch and finetuning from pre-trained models., Comment: NIPS 2022 Oral

This paper constructs a leading macroeconomic indicator from microeconomic data using recent machine learning techniques. Using tree-based methods, we estimate probabilities of default for publicly traded non-financial firms in the United States. We then use the cross-section of out-of-sample predicted default probabilities to construct a leading indicator of non-financial corporate health. The index predicts real economic outcomes such as GDP growth and employment up to eight quarters ahead. Impulse responses validate the interpretation of the index as a measure of financial stress. [ABSTRACT FROM AUTHOR]

Aggregate U.S. labor market dynamics are well approximated by a dual labor market supplemented with a third, predominantly, home-production segment. We uncover this structure by estimating a Hidden Markov Model, a machine-learning method. The different market segments are identified through (in-)equality constraints on labor market transition probabilities. This method yields time series of stocks and flows for the three segments for 1980-2021. Workers in the primary sector, who make up around 55 percent of the population, are almost always employed and rarely experience unemployment. The secondary sector, which constitutes 14 percent of the population, absorbs most of the short-run fluctuations, both at seasonal and business cycle frequencies. Workers in this segment experience six times higher turnover rates than those in the primary tier and are ten times more likely to be unemployed than their primary counterparts. The tertiary segment consists of workers who infrequently participate in the labor market but nevertheless experience unemployment when they try to enter the labor force. Our individual-level analysis shows that observable demographic characteristics only explain a small part of the cross-individual variation in segment membership. The combination of the aggregate and individual-level evidence we provide points to dualism in the U.S. labor market being an equilibrium division of labor, under labor market imperfections, that minimizes adjustment costs in response to predictable seasonal as well as unpredictable business cycle fluctuations. [ABSTRACT FROM AUTHOR]

We use machine learning techniques on textual data to identify financial crises. The onset of a crisis and its duration have implications for real economic activity, and as such can be valuable inputs into macroprudential, monetary, and fiscal policy. The academic literature and the policy realm rely mostly on expert judgment to determine crises, often with a lag. Consequently, crisis durations and the buildup phases of vulnerabilities are usually determined only with the benefit of hindsight. Although we can identify and forecast a portion of crises worldwide to various degrees with traditional econometric techniques and using readily available market data, we find that textual data helps in reducing false positives and false negatives in out-of-sample testing of such models, especially when the crises are considered more severe. Building a framework that is consistent across countries and in real time can benefit policymakers around the world, especially when international coordination is required across different government policies. [ABSTRACT FROM AUTHOR]

We develop a model that permits the estimation of a term structure of both expectations and forecast uncertainty for application to professional forecasts such as the Survey of Professional Forecasters (SPF). Our approach exactly replicates a given data set of predictions from the SPF (or a similar forecast source) without measurement error. Our model captures fixedhorizon and fixed-event forecasts, and can accommodate changes in the maximal forecast horizon available from the SPF. The model casts a decomposition of multi-period forecast errors into a sequence of forecast updates that may be partially unobserved, resulting in a multivariate unobserved components model. In our empirical analysis, we provide quarterly term structures of expectations and uncertainty bands. Our preferred specification features stochastic volatility in forecast updates, which improves forecast performance and yields model estimates of forecast uncertainty that vary over time. We conclude by constructing SPF-based fan charts for calendar-year forecasts like those published by the Federal Reserve. [ABSTRACT FROM AUTHOR]

Small and Medium-sized Enterprises (SMEs) could play a pivotal role in the pursuit of climate objectives. SMEs have a significant carbon footprint on aggregate, but they can also contribute to reaching net zero through their innovations and commitment to the use of environmentally friendly practices. This study develops a novel metric to identify environmental engagement, also referred to as "greening". The study harnesses the power of machine-learning and analyses the content of over one million websites of firms from 15 OECD countries encompassing about 10 billion words. Greening is identified based on firms' self-declared information about products or processes on their websites. The resulting indicator is then evaluated considering firms' characteristics. The results show that: (1) About one-third of SMEs are environmentally engaged, albeit with considerable variations across countries; (2) Greening SMEs are more productive, pay higher wages and their sales grow faster than nongreening SMEs; (3) Solar energy is the most cited action among greening SMEs, followed by recycling and energy efficiency, (4) Sectors with higher greenhouse gas emission reduction over the past decade also display higher levels of environmental engagement. [ABSTRACT FROM AUTHOR]

The article explores seasonal adjustment methods for consumer price indexes (CPI). It discusses the use of an X-12/X-13 method and standard econometric tests by national statistical offices (NSO). It examines the use of machine learning, particularly neural networks, in improving seasonal adjustment of CPI.

Copyright of Bornimer Agrartechnische Berichte is the property of Leibniz-Institut fur Agrartechnik und Biookonomie e.V. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The author reflects on the significance of Jack Hills in Western Australia, particularly its contribution to understanding the early Earth's continental crust through the discovery of ancient zircon grains. Topics include the geological history of the Jack Hills Belt, the implications of zircon age data, and recent research utilizing machine learning to analyze the composition of these ancient zircon grains, suggesting early continental crust exposure and tectonic activity.

We propose a coherent framework using support vector regression (SVR) for generating and ranking a set of high quality models for predicting emerging market sovereign credit spreads. Our framework adapts a global optimization algorithm employing an hv-block cross-validation metric, pertinent for models with serially correlated economic variables, to produce robust sets of tuning parameters for SVR kernel functions. In contrast to previous approaches identifying a single "best" tuning parameter setting, a task that is pragmatically improbable to achieve in many applications, we proceed with a collection of tuning parameter candidates, employing the Model Confidence Set test to select the most accurate models from the collection of promising candidates. Using bond credit spread data for three large emerging market economies and an array of input variables motivated by economic theory, we apply our framework to identify relatively small sets of SVR models with superior out-of-sample forecasting performance. Benchmarking our SVR forecasts against random walk and conventional linear model forecasts provides evidence for the notably superior forecasting accuracy of SVR-based models. In contrast to routinely used linear model benchmarks, the SVR-based models can generate accurate forecasts using only a small set of input variables limited to the country-specific credit-spread-curve factors, lending some support to the rational expectation theory of the term structure in the context of emerging market credit spreads. Consequently, our evidence indicates a better ability of highly flexible SVR to capture investor expectations about future spreads reflected in today's credit spread curve. [ABSTRACT FROM AUTHOR]

The article focuses on the evolving adoption of artificial intelligence (AI) and machine learning (ML) in the financial services industry, driven by technology advancements and automation. It discusses how AI/ML technologies have been integrated into various financial functions, such as customer service, investment identification, lending models, and fraud prevention, while policymakers grapple with regulatory challenges to ensure compliance and address potential risks.

We introduce a new software package for determining linkages between datasets without common identifiers. We apply these methods to three datasets commonly used in academic research on syndicated lending: Refinitiv LPC DealScan, the Shared National Credit Database, and S&P Global Market Intelligence Compustat. We benchmark the results of our match using results from the literature and previously matched files that are publicly available. We find that the company level matching is enhanced by careful cleaning of the data and considering hierarchical relationships. For loan level matching, a tailored approach based on a good understanding of the data can be better in certain dimensions than a more pure machine learning approach. The R package for the company level match can be found on Github at https://github.com/seunglee98/fedmatch. [ABSTRACT FROM AUTHOR]

This work addresses a real-life problem corresponding to the separation of the nonlinear mixture of images which arises when we scan a paper document and the image from the back page shows through. The proposed solution consists of a non-iterative procedure that is based on two simple observations: (1) the high frequency content of images is sparse, and (2) the image printed on each side of the paper appears more strongly in the mixture acquired from that side than in the mixture acquired from the opposite side. These ideas had already been used in the context of nonlinear denoising source separation (DSS). However, in that method the degree of separation achieved by applying these ideas was relatively weak, and the separation had to be improved by iterating within the DSS scheme. In this paper the application of these ideas is improved by changing the competition function and the wavelet transform that is used. These improvements allow us to achieve a good separation in one shot, without the need to integrate the process into an iterative DSS scheme. The resulting separation process is both nonlinear and non-local. We present experimental results that show that the method achieves a good separation quality.

When acquiring an image of a paper document, the image printed on the back page sometimes shows through. The mixture of the front- and back-page images thus obtained is markedly nonlinear, and thus constitutes a good real-life test case for nonlinear blind source separation. This paper addresses a difficult version of this problem, corresponding to the use of "onion skin" paper, which results in a relatively strong nonlinearity of the mixture, which becomes close to singular in the lighter regions of the images. The separation is achieved through the MISEP technique, which is an extension of the well known INFOMAX method. The separation results are assessed with objective quality measures. They show an improvement over the results obtained with linear separation, but have room for further improvement.

Many academic journals ask their authors to provide a list of about five to fifteen key words, to appear on the first page of each article. Since these key words are often phrases of two or more words, we prefer to call them keyphrases. There is a surprisingly wide variety of tasks for which keyphrases are useful, as we discuss in this paper. Recent commercial software, such as Microsoft?s Word 97 and Verity?s Search 97, includes algorithms that automatically extract keyphrases from documents. In this paper, we approach the problem of automatically extracting keyphrases from text as a supervised learning task. We treat a document as a set of phrases, which the learning algorithm must learn to classify as positive or negative examples of keyphrases. Our first set of experiments applies the C4.5 decision tree induction algorithm to this learning task. The second set of experiments applies the GenEx algorithm to the task. We developed the GenEx algorithm specifically for this task. The third set of experiments examines the performance of GenEx on the task of metadata generation, relative to the performance of Microsoft?s Word 97. The fourth and final set of experiments investigates the performance of GenEx on the task of highlighting, relative to Verity?s Search 97. The experimental results support the claim that a specialized learning algorithm (GenEx) can generate better keyphrases than a general-purpose learning algorithm (C4.5) and the non-learning algorithms that are used in commercial software (Word 97 and Search 97).

The article presents a reports of the U.S. Congressional Research Service, related to the development of financial technology in the U.S. It mentions that an increased availability and use of the internet and mobile devices could offer greater convenience and access to financial services. It mentions that technologies of machine learning and artificial intelligence could result in faster and more accurate assessments.

There is now a huge amount of interest in consciousness among scientists as well as philosophers, yet there is so much confusion and ambiguity in the claims and counter-claims that it is hard to tell whether any progress is being made. This ``position paper'' suggests that we can make progress by temporarily putting to one side questions about what consciousness is or which animals or machines have it or how it evolved. Instead we should focus on questions about the sorts of architectures that are possible for behaving systems and ask what sorts of capabilities, states and processes, might be supported by different sorts of architectures. We can then ask which organisms and machines have which sorts of architectures. This combines the standpoint of philosopher, biologist and engineer. If we can find a general theory of the variety of possible architectures (a characterisation of ``design space'') and the variety of environments, tasks and roles to which such architectures are well suited (a characterisation of ``niche space'') we may be able to use such a theory as a basis for formulating new more precisely defined concepts with which to articulate less ambiguous questions about the space of possible minds. For instance our initially ill-defined concept (``consciousness'') might split into a collection of more precisely defined concepts which can be used to ask unambiguous questions with definite answers. As a first step this paper explores a collection of conjectures regarding architectures and their evolution. In particular we explore architectures involving a combination of coexisting architectural levels including: (a) reactive mechanisms which evolved very early, (b) deliberative mechanisms which evolved later in response to pressures on information processing resources and (c) meta-management mechanisms that can explicitly inspect evaluate and modify some of the contents of various internal information structures. It is conjectured that in response to the needs of these layers, perceptual and action subsystems also developed layers, and also that an ``alarm'' system which initially existed only within the reactive layer may have become increasingly sophisticated and extensive as its inputs and outputs were linked to the newer layers. Processes involving the meta-management layer in the architecture could explain the origin of the notion of ``qualia''. Processes involving the ``alarm'' mechanism and mechanisms concerned with resource limits in the second and third layers gives us an explanation of three main forms of emotion, helping to account for some of the ambiguities which have bedevilled the study of emotion. Further theoretical and practical benefits may come from further work based on this design-based approach to consciousness. A deeper longer term implication is the possibility of a new science investigating laws governing possible trajectories in design space and niche space, as these form parts of high order feedback loops in the biosphere.

This paper discusses interdisciplinary experiments, combining robotics and evolutionary computational linguistics. The goal of the experiments is to investigate if robotic agents can originate a language, in particular a lexicon. In the experiments two robots engage in a series of so-called language games. Starting from the assumption that the robots know how to communicate and are able to detect some sensory information from the environment, the agents ground conceptual meaning and develop a lexicon. The experiments show that the robots are able to form a shared communication system. The paper investigates the influence of using non-linguistic information in the formation of the lexicon, which takes the form of pointing (1) to indicate the topic of the language game, and (2) to give feedback on the outcome of the game.

Using close to 40 years of textual data from FOMC transcripts and the Federal Reserve staff’s Greenbook/Tealbook, we extend Romer and Romer (2008) to test if the FOMC adds information relative to its staff forecasts not via its own quantitative forecasts but via its words. We use methods from natural language processing to extract from both types of document text-based forecasts that capture attentiveness to and sentiment about the macroeconomy. We test whether these text-based forecasts provide value-added in explaining the distribution of outcomes for GDP growth, the unemployment rate, and inflation. We find that FOMC tales about macroeconomic risks do add value in the tails, especially for GDP growth and the unemployment rate. For inflation, we find value-added in both FOMC point forecasts and narrative, once we extract from the text a broader set of measures of macroeconomic sentiment and risk attentiveness. [ABSTRACT FROM AUTHOR]

Using the results of a comprehensive in-person survey of properties in Cleveland, Ohio, we fit predictive models of vacancy and property conditions. We draw predictor variables from administrative data that is available in most jurisdictions such as deed recordings, tax assessor's property characteristics, and foreclosure filings. Using logistic regression and machine learning methods, we are able to make reasonably accurate out-of-sample predictions. Our findings indicate that housing professionals could use administrative data and predictive models to identify distressed properties between surveys or among nonsurveyed properties in an area subject to a random sample survey. [ABSTRACT FROM AUTHOR]

The article examines the results of a study on the presence of seasonality in consumer price indexes (CPI) in Organization for Economic Cooperation and Development countries. It describes the properties and performance of the X-13 and TRAMO-SEATS methods for seasonal adjustments of CPI. It discusses the potential of using machine learning to improve seasonal detection tests.

Methods of machine learning are used to recognize the soil type during soil compaction with attachment compactors. Acceleration records are measured on the vibratory plate. They are influenced by the Plate-soil-interaction and show characteristic patterns for different soil types and their humidities. The signal is processed in the frequency domain. 24 Dimensions are used for the feature extraction. Three soil classes with three relative humidities each can be detected. Together with the positioning of an excavator control system (GNSS-Position) a full 3D - protocol of the compacted soil and its densitiy ist provided. The novelty is that no calibration of the compaction control value to the proctor density is necessary. [ABSTRACT FROM AUTHOR]

The article focuses on semiconductors are tiny electronic devices composed of billions of components that can process, store, sense, and move data or signals. It mentions advancing semiconductor performance is vital for enabling fast-growing market demands such as machine learning, vehicle electrification, and high-performance computing, and supporting U.S. national security interests. It also mentions supply chain resiliency for the production of mature chip technologies.

IAMBIC AI is a company that is revolutionizing the footwear supply chain by using data science and technology to create personalized fit footwear. Through a three-step process, customers can order shoes on the company's website and then use a smartphone app to scan their feet and share data on their fit preferences. This data is then used by IAMBIC's AI machine learning model to personalize the shoe last or shoe mold. The company's technology has the potential to transform the footwear industry by making custom-fit footwear more accessible and cost-effective, while also reducing waste. IAMBIC has received recognition and funding for its innovative approach and plans to expand its offerings to include dress shoes and boots. The company is open to collaborations with other fashion brands and retailers to improve sizing and fit options. IAMBIC aims to be part of the slow fashion movement by encouraging consumers to be mindful with their purchases and to invest in long-lasting, quality products. The company's biggest challenges include recruiting engineering talent and building brand awareness for its unique approach to footwear. [Extracted from the article]

We use machine learning methods to examine the power of Treasury term spreads and other financial market and macroeconomic variables to forecast US recessions, vis-à-vis probit regression. In particular we propose a novel strategy for conducting cross-validation on classifiers trained with macro/financial panel data of low frequency and compare the results to those obtained from standard k-folds cross-validation. Consistent with the existing literature we find that, in the time series setting, forecast accuracy estimates derived from k-folds are biased optimistically, and cross-validation strategies which eliminate data "peeking" produce lower, and perhaps more realistic, estimates of forecast accuracy. More strikingly, we also document rank reversal of probit, Random Forest, XGBoost, LightGBM, neural network and support-vector machine classifier forecast performance over the two cross-validation methodologies. That is, while a k-folds cross-validation indicates that the forecast accuracy of tree methods dominates that of neural networks, which in turn dominates that of probit regression, the more conservative cross-validation strategy we propose indicates the exact opposite, and that probit regression should be preferred over machine learning methods, at least in the context of the present problem. This latter result stands in contrast to a growing body of literature demonstrating that machine learning methods outperform many alternative classification algorithms and we discuss some possible reasons for our result. We also discuss techniques for conducting statistical inference on machine learning classifiers using Cochrane's Q and McNemar's tests; and use the SHapley Additive exPlanations (SHAP) framework to decompose US recession forecasts and analyze feature importance across business cycles. [ABSTRACT FROM AUTHOR]

Using novel methodology and proprietary daily store-level apparel and sporting goods brand data, I find that, consistent with long-run adaptation to climate, sales sensitivity to weather declines as historical norms and variability of weather increase. Short-run adaptation to weather shocks is dominated by changes in how much people buy on the day of the event. There is little intertemporal substitution. Over four weeks, a one-standard deviation one-day weather shock shifts sales by about 10 percent. While switching between indoor and outdoor stores offsets a small portion of contemporaneous responses, I find no evidence that ecommerce offsets any of the effects. [ABSTRACT FROM AUTHOR]

Using novel methodology and proprietary daily store-level apparel and sporting goods brand data, I find that, consistent with long-run adaptation to climate, sales sensitivity to weather declines as historical norms and variability of weather increase. Short-run adaptation to weather shocks is dominated by changes in how much people buy on the day of the event. There is little intertemporal substitution. Over four weeks, a one-standard deviation one-day weather shock shifts sales by about 10 percent. While switching between indoor and outdoor stores offsets a small portion of contemporaneous responses, I find no evidence that ecommerce offsets any of the effects. [ABSTRACT FROM AUTHOR]