Explainable AI Models Research Articles

Which SME is worth an investment? An explainable machine learning approach

Investments in Small and Medium Enterprise (SME) are facilitated by the availability of advanced machine learning (ML) methods, with high computational power and accuracy. However, despite their high accuracy, complex ML models do not provide sufficient explanation and may not be adequate for informed decision-making. In this paper, we propose an explainable AI model that can be used for analyzing SMEs and, in particular, for predicting their expected return, based on their credit risk and expected profitability. Our model is based on Shapley values which allow the predicted values generated by AI models to be interpreted according to the available explanatory variables. To validate our model we have extracted financial performance indicators from the annual balance sheets of 2049 SMEs. As a result of our empirical analysis, we show that the expected return of SMEs can be well predicted and explained by a set of characteristics deduced from their balance sheets. Therefore, their future behavior including risk and return can be predicted.

Explainable AI for Multimodal Credibility Analysis: Case Study of Online Beauty Health (Mis)-Information

“One person’s data or experience is another person’s information” this has become the golden rule of the 21st century which has resulted in a massive reservoir of data and immense amounts of information generation. However, there is no control over the source of this information, accessibility of this information, or the quality of it, which has given rise to the presence of “misinformation.” The research community has reacted by proposing frameworks and difficulties, which are helpful for (different subtasks of) recognizing misinformation. Most of these frameworks, however, fail to consider all the aspects that can contribute to making information “credible”. Furthermore, a valid explanation for each considered feature’s contribution to the model’s decision stands missing in most work. With this in mind, the authors have attempted to produce a system that yields highly accurate decisions, thus effectively separating credible health blogs from their non-credible counterparts while providing valid user-friendly explanations. The study proposes an Explainable AI-assisted Multimodal Credibility Assessment System that examines the credibility of the platform where the blog is hosted, the credibility of the author of the blog and the credibility of the images that contribute to the blog. This novel framework contributes to the existing body of knowledge by assessing the credibility of misleading beauty blogs using multiple crucial modalities which would lead to an insightful information consumption by the users. The proposed pipeline was successfully implemented on multiple carefully curated datasets and correctly identified 274 non credible blogs out of 321 blogs with an accuracy of 97.5%, Precision of 0.973 & F1score of 0.986. Further, the Explainable AI model, with the help of several visualizations displayed the feature contributions for each blog & it’s impact and magnitude in a concise comprehensible format. The framework can be further customized and applied to various domains where presence of misinformation is of high concern such as pharmaceutical drug information, pandemic management, financial advisories, online healthcare services and cyber frauds.

Explainable AI (XAI) Models Applied to Planning in Financial Markets

Regime changes planning in financial markets is well known to be hard to explain and interpret. Can an asset manager ex-plain clearly the intuition of his regime changes prediction on equity market ? To answer this question, we consider a gradi-ent boosting decision trees (GBDT) approach to plan regime changes on S&P 500 from a set of 150 technical, fundamen-tal and macroeconomic features. We report an improved ac-curacy of GBDT over other machine learning (ML) methods on the S&P 500 futures prices. We show that retaining fewer and carefully selected features provides improvements across all ML approaches. Shapley values have recently been intro-duced from game theory to the field of ML. This approach allows a robust identification of the most important variables planning stock market crises, and of a local explanation of the crisis probability at each date, through a consistent features attribution. We apply this methodology to analyse in detail the March 2020 financial meltdown, for which the model of-fered a timely out of sample prediction. This analysis unveils in particular the contrarian predictive role of the tech equity sector before and after the crash.

Explainable AI Models of Stock Crashes: A Machine-Learning Explanation of the Covid March 2020 Equity Meltdown

We consider a gradient boosting decision trees (GBDT) approach to predict large S&P 500 price drops from a set of 150 technical, fundamental and macroeconomic features. We report an improved accuracy of GBDT over other machine learning (ML) methods on the S&P 500 futures prices. We show that retaining fewer and carefully selected features provides improvements across all ML approaches. Shapley values have recently been introduced from game theory to the field of ML. They allow for a robust identification of the most important variables predicting stock market crises, and of a local explanation of the crisis probability at each date, through a consistent features attribution. We apply this methodology to analyze in detail the March 2020 financial meltdown, for which the model offered a timely out of sample prediction. This analysis unveils in particular the contrarian predictive role of the tech equity sector before and after the crash.

Why to Buy Insurance? An Explainable Artificial Intelligence Approach

We propose an Explainable AI model that can be employed in order to explain why a customer buys or abandons a non-life insurance coverage. The method consists in applying similarity clustering to the Shapley values that were obtained from a highly accurate XGBoost predictive classification algorithm. Our proposed method can be embedded into a technologically-based insurance service (Insurtech), allowing to understand, in real time, the factors that most contribute to customers’ decisions, thereby gaining proactive insights on their needs. We prove the validity of our model with an empirical analysis that was conducted on data regarding purchases of insurance micro-policies. Two aspects are investigated: the propensity to buy an insurance policy and the risk of churn of an existing customer. The results from the analysis reveal that customers can be effectively and quickly grouped according to a similar set of characteristics, which can predict their buying or churn behaviour well.

Potentially adaptive SARS-CoV-2 mutations discovered with novel spatiotemporal and explainable AI models

BackgroundA mechanistic understanding of the spread of SARS-CoV-2 and diligent tracking of ongoing mutagenesis are of key importance to plan robust strategies for confining its transmission. Large numbers of available sequences and their dates of transmission provide an unprecedented opportunity to analyze evolutionary adaptation in novel ways. Addition of high-resolution structural information can reveal the functional basis of these processes at the molecular level. Integrated systems biology-directed analyses of these data layers afford valuable insights to build a global understanding of the COVID-19 pandemic.ResultsHere we identify globally distributed haplotypes from 15,789 SARS-CoV-2 genomes and model their success based on their duration, dispersal, and frequency in the host population. Our models identify mutations that are likely compensatory adaptive changes that allowed for rapid expansion of the virus. Functional predictions from structural analyses indicate that, contrary to previous reports, the Asp614Gly mutation in the spike glycoprotein (S) likely reduced transmission and the subsequent Pro323Leu mutation in the RNA-dependent RNA polymerase led to the precipitous spread of the virus. Our model also suggests that two mutations in the nsp13 helicase allowed for the adaptation of the virus to the Pacific Northwest of the USA. Finally, our explainable artificial intelligence algorithm identified a mutational hotspot in the sequence of S that also displays a signature of positive selection and may have implications for tissue or cell-specific expression of the virus.ConclusionsThese results provide valuable insights for the development of drugs and surveillance strategies to combat the current and future pandemics.

XAI-EWS — an explainable AI model predicting acute critical illness

xAI-EWS — an explainable AI model predicting acute critical illness

Use of artificial intelligence based models for learning better policy for maternal and child health

Abstract More than 640,000 babies died of sepsis before they reach the age of one month in India in 2016. Despite a large number of government schemes aimed at reducing this rate, this number still remains high because of the complexity and interplay of factors involved. Finding an optimum policy and solutions to this problem needs learning from data. We integrated diverse sources of data and applied Bayesian Artificial Intelligence methods for learning to mitigate sepsis and adverse pregnancy outcomes in India. In this project, we created models that combine the robustness of ensemble averaged Baeysian Networks with decision learning and impact evaluation by using simulations and counterfactual reasoning respectively. We will demonstrate the process of learning these models and how these led us to infer the pivotal role of Water, Sanitation and Hygiene for reducing Adverse Pregnancy Outcome and neonatal sepsis in the population studied. We will also demonstrate the creation of explainable AI models for complex public health challenges and their deployment with wiseR, our in-house, open source platform for doing end-to-end Bayesian Decision Network learning.

Explainable AI in Fintech Risk Management.

The paper proposes an explainable AI model that can be used in fintech risk management and, in particular, in measuring the risks that arise when credit is borrowed employing peer to peer lending platforms. The model employs Shapley values, so that AI predictions are interpreted according to the underlying explanatory variables. The empirical analysis of 15,000 small and medium companies asking for peer to peer lending credit reveals that both risky and not risky borrowers can be grouped according to a set of similar financial characteristics, which can be employed to explain and understand their credit score and, therefore, to predict their future behavior.

CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines

We present CoCoX (short for Conceptual and Counterfactual Explanations), a model for explaining decisions made by a deep convolutional neural network (CNN). In Cognitive Psychology, the factors (or semantic-level features) that humans zoom in on when they imagine an alternative to a model prediction are often referred to as fault-lines. Motivated by this, our CoCoX model explains decisions made by a CNN using fault-lines. Specifically, given an input image I for which a CNN classification model M predicts class cpred, our fault-line based explanation identifies the minimal semantic-level features (e.g., stripes on zebra, pointed ears of dog), referred to as explainable concepts, that need to be added to or deleted from I in order to alter the classification category of I by M to another specified class calt. We argue that, due to the conceptual and counterfactual nature of fault-lines, our CoCoX explanations are practical and more natural for both expert and non-expert users to understand the internal workings of complex deep learning models. Extensive quantitative and qualitative experiments verify our hypotheses, showing that CoCoX significantly outperforms the state-of-the-art explainable AI models. Our implementation is available at https://github.com/arjunakula/CoCoX

Shapley-Lorenz Decompositions in eXplainable Artificial Intelligence

Explainability of artificial intelligence models has become a crucial issue, especially in the most regulated fields, such as health and finance. In this paper, we provide a global explainable AI model which is based on Lorenz decompositions, thus extending previous contributions based on variance decompositions. This allows the resulting Shapley Lorenz decomposition to be more generally applicable, and provides a unifying variable importance criteria that combines predictive accuracy with explainability, using a normalised and easy to interpret metric. The proposed decomposition is illustrated within the context of a real financial problem: the prediction of bitcoin prices.

Explainable AI in Credit Risk Management

The paper proposes an explainable AI model that can be used in credit risk management and, in particular, in measuring the risks that arise when credit is borrowed employing credit scoring platforms. The model applies similarity networks to Shapley values, so that AI predictions are grouped according to the similarity in the underlying explanatory variables. The empirical analysis of 15,000 small and medium companies asking for credit reveals that both risky and not risky borrowers can be grouped according to a set of similar financial characteristics, which can be employed to explain and understand their credit score and, therefore, to predict their future behaviour.