Financial Machine Learning

Can Machine Learning Decode Depression?

Machine-Learning Implementation in Clinical Anesthesia: Opportunities and Challenges.

Special issue on machine learning and quantum mechanics

No-code machine learning (ML) tools provide an avenue for individuals who lack advanced ML skills to develop ML applications. Extant literature indicates that by using such tools, individuals can acquire relevant ML skills. However, no explanation has been provided of how the use of no-code ML tools leads to the generation of these skills. Using the theory of technology affordances and constraints, this article undertakes a qualitative evaluation of publicly available no-code ML tools to explain how their usage can lead to the formation of relevant ML skills. Subsequently, the authors show that no-code ML tools generate familiarization affordances, utilization affordances, and administration affordances. Subsequently, they provide a conceptual framework and process model that depicts how these affordances lead to the generating of ML skills.

Machine learning (ML) tools reduce the costs of performing repetitive, time-consuming tasks yet run the risk of introducing systematic unfairness into organizational processes. Automated approaches to achieving fairness often fail in complex situations, leading some researchers to suggest that human augmentation of ML tools is necessary. However, our current understanding of human–ML augmentation remains limited. In this paper, we argue that the Information Systems (IS) discipline needs a more sophisticated view of and research into human–ML augmentation. We introduce a typology of augmentation for fairness consisting of four quadrants: reactive oversight, proactive oversight, informed reliance, and supervised reliance. We identify significant intersections with previous IS research and distinct managerial approaches to fairness for each quadrant. Several potential research questions emerge from fundamental differences between ML tools trained on data and traditional IS built with code. IS researchers may discover that the differences of ML tools undermine some of the fundamental assumptions upon which classic IS theories and concepts rest. ML may require massive rethinking of significant portions of the corpus of IS research in light of these differences, representing an exciting frontier for research into human–ML augmentation in the years ahead that IS researchers should embrace. 1

Ethical limitations of algorithmic fairness solutions in health care machine learning

Machine learning for predicting opioid use disorder from healthcare data: A systematic review

PurposeEnvironmental, social and governance (ESG) factors have become increasingly important in investment decisions, leading to a surge in ESG investing and the rise of sustainable investment assets. Nevertheless, challenges in ESG disclosure, such as quantifying unstructured data, lack of guidelines and comparability, rampantly exist. ESG rating agencies play a crucial role in assessing corporate ESG performance, but concerns over their credibility and reliability persist. To address these issues, researchers are increasingly utilizing machine learning (ML) tools to enhance ESG reporting and evaluation. By leveraging ML, accounting practitioners and researchers gain deeper insights into the relationship between ESG practices and financial performance, offering a more data-driven understanding of ESG impacts on business communities.Design/methodology/approachThe authors review the current research on ESG disclosure and ESG performance disagreement, followed by the review of current ESG research with ML tools in three areas: connecting ML with ESG disclosures, integrating ML with ESG rating disagreement and employing ML with ESG in other settings. By comparing different research's ML applications in ESG research, the authors conclude the positive and negative sides of those research studies.FindingsThe practice of ESG reporting and assurance is on the rise, but still in its technical infancy. ML methods offer advantages over traditional approaches in accounting, efficiently handling large, unstructured data and capturing complex patterns, contributing to their superiority. ML methods excel in prediction accuracy, making them ideal for tasks like fraud detection and financial forecasting. Their adaptability and feature interaction capabilities make them well-suited for addressing diverse and evolving accounting problems, surpassing traditional methods in accuracy and insight.Originality/valueThe authors broadly review the accounting research with the ML method in ESG-related issues. By emphasizing the advantages of ML compared to traditional methods, the authors offer suggestions for future research in ML applications in ESG-related fields.

In the past few years, machine learning (ML) tools have been implemented with success in the medical context. However, several practitioners have raised concerns about the lack of transparency—at the algorithmic level—of many of these tools; and solutions from the field of explainable AI (XAI) have been seen as a way to open the ‘black box’ and make the tools more trustworthy. Recently, Alex London has argued that in the medical context we do not need machine learning tools to be interpretable at the algorithmic level to make them trustworthy, as long as they meet some strict empirical desiderata. In this paper, we analyse and develop London’s position. In particular, we make two claims. First, we claim that London’s solution to the problem of trust can potentially address another problem, which is how to evaluate the reliability of ML tools in medicine for regulatory purposes. Second, we claim that to deal with this problem, we need to develop London’s views by shifting the focus from the opacity of algorithmic details to the opacity of the way in which ML tools are trained and built. We claim that to regulate AI tools and evaluate their reliability, agencies need an explanation of how ML tools have been built, which requires documenting and justifying the technical choices that practitioners have made in designing such tools. This is because different algorithmic designs may lead to different outcomes, and to the realization of different purposes. However, given that technical choices underlying algorithmic design are shaped by value-laden considerations, opening the black box of the design process means also making transparent and motivating (technical and ethical) values and preferences behind such choices. Using tools from philosophy of technology and philosophy of science, we elaborate a framework showing how an explanation of the training processes of ML tools in medicine should look like.

Using Machine Learning Classification to Predict Social Inferencing Performance from Eye-tracking Data in Participants with and without Brain Injury

ADRD caregivers increasingly use social media to meet their health information wants (HIW). Machine learning (ML) tools may help understand caregivers’ HIW as expressed via social media. This pilot study explored a collaborative, iterative process between domain experts and ML tools to identify ADRD caregivers’ HIW from social media data. The HIW-ADRD framework was adapted from an existing HIW framework. Through multiple rounds of iteration between the experts and the ML tools, the framework was expanded to include 11 types of health information. Each type included corresponding keywords developed through a hybrid approach that included keywords from both the theoretical constructs (top-down) and caregivers’ posts (bottom-up). These keywords were then used to enhance the ML tools’ ability to code 106 recent posts extracted from an ADRD social media group in March 2020. When compared with expert coding results, ML tools accurately predicted 56% of HIW. Further work is underway.

Machine Learning Algorithm Prospectively Predicts Survival for High-Risk Patients Undergoing Radiotherapy: A Survival Analysis of SHIELD-RT

This study systematically benchmarks a variety of machine learning (ML) tools for their application in automotive embedded controls, with a particular focus on engine control units (ECUs). The advent of ML in the automotive industry has catalyzed significant advancements in vehicle automation, enhancing safety, efficiency, and performance. However, the deployment of ML technologies in embedded automotive systems presents unique challenges due to the stringent requirements for real-time processing and limited computational resources. In this research, we evaluate several ML tools and frameworks, including both commercial software and custom-developed algorithms, to determine their suitability for real-time automotive applications. Using criteria such as computational efficiency, memory usage, and ease of integration with existing automotive systems, we provide a comprehensive comparison and analysis. The tools examined range from high-level programming environments like Python and MATLAB to specific commercial services tailored for embedded systems. Our findings reveal significant variations in the performance and applicability of these tools in an automotive context. We also discuss the implications of these findings for the design and optimization of ML-driven automotive systems. The outcomes of this study offer valuable insights for automotive engineers and system designers, aiding in the selection of optimal ML tools that meet the dual demands of performance and practical implementation in embedded systems. This research underscores the potential of ML to revolutionize automotive systems and lays the groundwork for future innovations in this rapidly evolving field.

The process of automatically recognising significant patterns within large amounts of data is called "machine learning." Throughout the last couple of decades, it has evolved into a tool used in almost every activity requiring the extraction of information from large data sets. We are surrounded by technology that is based on machine learning: Search engines are learning how to bring us the best results (while placing profitable ads), antispam software is learning how to filter our email messages, and credit card transactions are secured by software that learns how to detect frauds. Intelligent personal assistance software on smartphones can learn to recognise voice commands, and digital cameras can train themselves to identify faces. Accident-prevention systems in vehicles are constructed with the help of machine-learning algorithms. These systems are installed in modern automobiles. In addition, machine learning is extensively utilised in various scientific applications, including bioinformatics, medicine, and astronomy. One aspect that is shared by all of these applications is the fact that, in contrast to more conventional applications of computers, in these situations, due to the complexity of the patterns that need to be detected, a human programmer is unable to provide an explicit, fine-detailed specification of how such tasks should be carried out. This is one of the characteristics that make all of these applications unique. Taking cues from other intelligent beings, most of our capabilities have been obtained or improved via learning from our experiences (rather than following explicit instructions). Tools for machine learning are used to give computer programmes the capacity to "learn" and modify their behaviour on their own. The first objective of this book is to provide the fundamental ideas that comprehensively underpin machine learning while still being simple to understand. The process of automatically recognising significant patterns within large amounts of data is called "machine learning." Throughout the last couple of decades, it has evolved into a tool used in almost every activity requiring the extraction of information from large data sets. We are surrounded by technology that is based on machine learning: Search engines are learning how to bring us the best results (while placing profitable ads), antispam software is learning how to filter our email messages, and credit card transactions are secured by software that learns how to detect frauds. Intelligent personal assistance software on smartphones can learn to recognise voice commands, and digital cameras can train themselves to identify faces. Accident-prevention systems in vehicles are constructed with the help of machine-learning algorithms. These systems are installed in modern automobiles. In addition, machine learning is extensively utilised in various scientific applications, including bioinformatics, medicine, and astronomy. One aspect that is shared by all of these applications is the fact that, in contrast to more conventional applications of computers, in these situations, due to the complexity of the patterns that need to be detected, a human programmer is unable to provide an explicit, fine-detailed specification of how such tasks should be carried out. This is one of the characteristics that make all of these applications unique. Taking cues from other intelligent beings, most of our capabilities have been obtained or improved via learning from our experiences (rather than following explicit instructions). Tools for machine learning are used to give computer programmes the capacity to "learn" and modify their behaviour on their own. The first objective of this book is to provide the fundamental ideas that comprehensively underpin machine learning while still being simple to understand.

The advent of cloud-based super-computing platforms has given rise to a Data Science (DS) boom. Many types of technological problems that were once considered prohibitively expensive to tackle are now candidates for exploration. Machine Learning (ML) tools that were valued only in academic environments are quickly being embraced by industrial giants and tiny startups alike. Coupled with modern-day computing power, ML tools can be looked at as hammers that can deal with even the most stubborn nails. ML tools have become so ubiquitous that the current industrial expectation is that they should not only deliver accurate and intelligent solutions but also do so rapidly. In order to keep pace with these requirements, a new enterprise, referred to as MLOps has blossomed in recent years. MLOps combines the process of ML and DS with an agile software engineering technique to develop and deliver solutions in a fast and iterative way. One of the key challenges to this is that ML and DS tools should be efficient and have better usability characteristics than were traditionally offered. In this paper, we present a novel software for Grammatical Evolution (GE) that meets both of these expectations. Our tool, GELAB, is a toolbox for GE in Matlab which has numerous features that distinguish it from existing contemporary GE software. Firstly, it is user-friendly and its development was aimed for use by non-specialists. Secondly, it is capable of hybrid optimization, in which standard numerical optimization techniques can be added to GE. We have shown experimentally that when hybridized with meta-heuristics GELAB has an overall better performance as compared with standard GE.