The financial industry faces a significant challenge modeling and risk portfolios: balancing the predictability of advanced machine learning models, neural network models, and explainability required by regulatory entities (such as Office of the Comptroller of the Currency, Consumer Financial Protection Bureau). This paper intends to fill the gap in the application between these "black box" models and explainability frameworks, such as LIME and SHAP. Authors elaborate on the application of these frameworks on different models and demonstrates the more complex models with better prediction powers could be applied and reach the same level of the explainability, using SHAP and LIME. Beyond the comparison and discussion of performances, this paper proposes a novel five dimensional framework evaluating Inherent Interpretability, Global Explanations, Local Explanations, Consistency, and Complexity to offer a nuanced method for assessing and comparing model explainability beyond simple accuracy metrics. This research demonstrates the feasibility of employing sophisticated, high performing ML models in regulated financial environments by utilizing modern explainability techniques and provides a structured approach to evaluate the crucial trade offs between model performance and interpretability.

In speech emotion recognition (SER), using predefined features without considering their practical importance may lead to high dimensional datasets, including redundant and irrelevant information. Consequently, high-dimensional learning often results in decreasing model accuracy while increasing computational complexity. Our work underlines the importance of carefully considering and analyzing features in order to build efficient SER systems. We present a new supervised SER method based on an efficient feature engineering approach. We pay particular attention to the explainability of results to evaluate feature relevance and refine feature sets. This is performed iteratively through feature evaluation loop, using Shapley values to boost feature selection and improve overall framework performance. Our approach allows thus to balance the benefits between model performance and transparency. The proposed method outperforms human-level performance (HLP) and state-of-the-art machine learning methods in emotion recognition on the TESS dataset. The source code of this paper is publicly available at https://github.com/alaaNfissi/Iterative-Feature-Boosting-for-Explainable-Speech-Emotion-Recognition.

Adversarial attacks are a type of attack on machine learning models where an attacker deliberately modifies the inputs to cause the model to make incorrect predictions. Adversarial attacks can have serious consequences, particularly in applications such as autonomous vehicles, medical diagnosis, and security systems. Work on the vulnerability of deep learning models to adversarial attacks has shown that it is very easy to make samples that make a model predict things that it doesn't want to. In this work, we analyze the impact of model interpretability due to adversarial attacks on text classification problems. We develop an ML-based classification model for text data. Then, we introduce the adversarial perturbations on the text data to understand the classification performance after the attack. Subsequently, we analyze and interpret the model's explainability before and after the attack

The estimation and monitoring of SpO2 are crucial for assessing lung function and treating chronic pulmonary diseases. The COVID-19 pandemic has highlighted the importance of early detection of changes in SpO2, particularly in asymptomatic patients with clinical deterioration. However, conventional SpO2 measurement methods rely on contact-based sensing, presenting the risk of cross-contamination and complications in patients with impaired limb perfusion. Additionally, pulse oximeters may not be available in marginalized communities and undeveloped countries. To address these limitations and provide a more comfortable and unobtrusive way to monitor SpO2, recent studies have investigated SpO2 measurement using videos. However, measuring SpO2 using cameras in a contactless way, particularly from smartphones, is challenging due to weaker physiological signals and lower optical selectivity of smartphone camera sensors. The system includes three main steps: 1) extraction of the region of interest (ROI), which includes the palm and back of the hand, from the smartphone-captured videos; 2) spatial averaging of the ROI to produce R, G, and B time series; and 3) feeding the time series into an optophysiology-inspired CNN for SpO2 estimation. Our proposed method can provide a more efficient and accurate way to monitor SpO2 using videos captured from consumer-grade smartphones, which can be especially useful in telehealth and health screening settings.

Deep Learning (DL) advances have cleared the way for intriguing new applications and are influencing the future of Artificial Intelligence (AI) technology. However, a typical concern for DL models is their explainability, as experts commonly agree that Neural Networks (NNs) function as black boxes. We do not precisely know what happens inside, but we know that the given input is somehow processed, and as a result, we obtain something as output. For this reason, DL models can often be difficult to understand or interpret. Understanding why a model makes certain predictions or how to improve it can be challenging.

Transformers Interpret is a model explainability tool designed to work exclusively with the transformers package. In line with the philosophy of the Transformers package Transformers Interpret allows any transformers model to be explained in just two lines. Explainers are available for both text and computer vision models. Visualizations are also available in notebooks and as savable png and html files. Positive attribution numbers indicate a word contributes positively towards the predicted class, while negative numbers indicate a word contributes negatively towards the predicted class.

The most sophisticated AI language models, like OpenAI's GPT-3, can perform tasks from generating code to drafting marketing copy. But many of the underlying mechanisms remain opaque, making these models prone to unpredictable -- and sometimes toxic -- behavior. As recent research has shown, even careful calibration can't always prevent language models from making sexist associations or endorsing conspiracies. Newly proposed explainability techniques promise to make language models more transparent than before. While they aren't silver bullets, they could be the building blocks for less problematic models -- or at the very least models that can explain their reasoning.

A good place to start is Noga Gershon Barak's introduction to the open-source InterpretML package. Noga walks us through the ins and outs of the package, and focuses on Explainable Boosting Machine (EBM), "a glassbox model intended to have comparable accuracy to machine learning models such as Random Forest and Boosted Trees as well as interpretability capabilities." Not sure yet which approach is right for you? If you're taking your first steps in this area, it's understandable if you'd like to know a bit more about the various explainability methods out there. Vincent Margot's overview of XAI methods is an accessible entryway for learning about Partial Dependence Plot (PDP), Accumulated Local Effects (ALE), and Individual Conditional Expectation (ICE), among others.