Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, generally leading to overestimation of methods' real-world utility. In this work, we seek to address this by conducting a study that evaluates post-hoc explainable ML methods in a setting consistent with the application context and provide a template for future evaluation studies. We modify and improve a prior study on e-commerce fraud detection by relaxing the original work's simplifying assumptions that departed from the deployment context. Our study finds no evidence for the utility of the tested explainable ML methods in the context, which is a drastically different conclusion from the earlier work. This highlights how seemingly trivial experimental design choices can yield misleading conclusions about method utility. In addition, our work carries lessons about the necessity of not only evaluating explainable ML methods using tasks, data, users, and metrics grounded in the intended application context but also developing methods tailored to specific applications, moving beyond general-purpose explainable ML methods.

Data used by automated decision-making systems, such as Machine Learning models, often reflects discriminatory behavior that occurred in the past. These biases in the training data are sometimes related to label noise, such as in COMPAS, where more African-American offenders are wrongly labeled as having a higher risk of recidivism when compared to their White counterparts. Models trained on such biased data may perpetuate or even aggravate the biases with respect to sensitive information, such as gender, race, or age. However, while multiple label noise correction approaches are available in the literature, these focus on model performance exclusively. In this work, we propose Fair-OBNC, a label noise correction method with fairness considerations, to produce training datasets with measurable demographic parity. The presented method adapts Ordering-Based Noise Correction, with an adjusted criterion of ordering, based both on the margin of error of an ensemble, and the potential increase in the observed demographic parity of the dataset. We evaluate Fair-OBNC against other different pre-processing techniques, under different scenarios of controlled label noise. Our results show that the proposed method is the overall better alternative within the pool of label correction methods, being capable of attaining better reconstructions of the original labels. Models trained in the corrected data have an increase, on average, of 150% in demographic parity, when compared to models trained in data with noisy labels, across the considered levels of label noise.

Aequitas Flow is an open-source framework and toolkit for end-to-end Fair Machine Learning (ML) experimentation, and benchmarking in Python. This package fills integration gaps that exist in other fair ML packages. In addition to the existing audit capabilities in Aequitas, the Aequitas Flow module provides a pipeline for fairness-aware model training, hyperparameter optimization, and evaluation, enabling easy-to-use and rapid experiments and analysis of results. Aimed at ML practitioners and researchers, the framework offers implementations of methods, datasets, metrics, and standard interfaces for these components to improve extensibility. By facilitating the development of fair ML practices, Aequitas Flow hopes to enhance the incorporation of fairness concepts in AI systems making AI systems more robust and fair.

As data science and machine learning (ML) increasingly shape our society, the importance of developing fair algorithmic decision-making systems becomes paramount. There is a pressing need to train data scientists and practitioners on handling bias and fairness in real-world scenarios, from early stages of a data science project to maintaining ML systems in production. Existing resources are mostly academic and cover the ML training and optimization aspects of bias mitigation, leaving practitioners without comprehensive frameworks for making decisions throughout a real-world project lifecycle. This tutorial aims to bridge the gap between research and practice, providing an in-depth exploration of algorithmic fairness, encompassing metrics and definitions, practical case studies, data bias understanding, bias mitigation and model fairness audits using the Aequitas toolkit. Participants will be equipped to engage in conversations about bias, assist decision-makers in understanding options and trade-offs, evaluate project scoping aspects influencing fairness outcomes, and define actions and interventions based on model predictions. They will also learn to identify cohorts, target variables, evaluation metrics, and establish bias and fairness goals for different groups. Moreover, participants will gain insights into auditing and mitigating model bias, and implementing continuous monitoring to assess retraining needs. The tutorial addresses the current lack of practical training materials, methodologies, and tools for researchers and developers working on real-world algorithmic decision-making systems. By the conclusion of this hands-on tutorial, attendees will be well-versed in navigating bias-related issues, selecting appropriate metrics, and applying bias audit and mitigation frameworks and tools for informed design decisions in real-world data science systems.

Evaluating new techniques on realistic datasets plays a crucial role in the development of ML research and its broader adoption by practitioners. In recent years, there has been a significant increase of publicly available unstructured data resources for computer vision and NLP tasks. However, tabular data — which is prevalent in many high-stakes domains — has been lagging behind. To bridge this gap, we present Bank Account Fraud (BAF), the first publicly available 1 privacy-preserving, large-scale, realistic suite of tabular datasets. The suite was generated by applying state-of-the-art tabular data generation techniques on an anonymized,real-world bank account opening fraud detection dataset. This setting carries a set of challenges that are commonplace in real-world applications, including temporal dynamics and significant class imbalance. Additionally, to allow practitioners to stress test both performance and fairness of ML methods, each dataset variant of BAF contains specific types of data bias. With this resource, we aim to provide the research community with a more realistic, complete, and robust test bed to evaluate novel and existing methods.

Considerable research effort has been guided towards algorithmic fairness but real-world adoption of bias reduction techniques is still scarce. Existing methods are either metric-or model-specific, require access to sensitive attributes at inference time, or carry high development or deployment costs. This work explores the unfairness that emerges when optimizing ML models solely for predictive performance, and how to mitigate it with a simple and easily deployed intervention: fairness-aware hyperparameter optimization (HO). We propose and evaluate fairness-aware variants of three popular HO algorithms: Fair Random Search, Fair TPE, and Fairband. We validate our approach on a real-world bank account opening fraud case-study, as well as on three datasets from the fairness literature. Results show that, without extra training cost, it is feasible to find models with 111% mean fairness increase and just 6% decrease in performance when compared with fairness-blind HO.1

Although recurrent neural networks (RNNs) are state-of-the-art in numerous sequential decision-making tasks, there has been little research on explaining their predictions. In this work, we present TimeSHAP, a model-agnostic recurrent explainer that builds upon KernelSHAP and extends it to the sequential domain. TimeSHAP computes feature-, timestep-, and cell-level attributions. As sequences may be arbitrarily long, we further propose a pruning method that is shown to dramatically decrease both its computational cost and the variance of its attributions. We use TimeSHAP to explain the predictions of a real-world bank account takeover fraud detection RNN model, and draw key insights from its explanations: i) the model identifies important features and events aligned with what fraud analysts consider cues for account takeover; ii) positive predicted sequences can be pruned to only 10% of the original length, as older events have residual attribution values; iii) the most recent input event of positive predictions only contributes on average to 41% of the model's score; iv) notably high attribution to client's age, upheld on higher false positive rates for older clients.

Tackling issues of bias and fairness when building and deploying data science systems has received increased attention from the research community in recent years, yet a lot of the research has focused on theoretical aspects and very limited set of application areas and data sets. There is a lack of 1) practical training materials, 2) methodologies, and 3) tools for researchers and developers working on real-world algorithmic decision making system to deal with issues of bias and fairness. Today, treating bias and fairness as primary metrics of interest, and building, selecting, and validating models using those metrics is not standard practice for data scientists. In this hands-on tutorial we will try to bridge the gap between research and practice, by deep diving into algorithmic fairness, from metrics and definitions to practical case studies, including bias audits using the Aequitas toolkit (http://github.com/dssg/aequitas). By the end of this hands-on tutorial, the audience will be familiar with bias mitigation frameworks and tools to help them making decisions during a project based on intervention and deployment contexts in which their system will be used.

E-commerce platforms facilitate sales of products while product vendors engage in Social Media Activities (SMA) to drive E-commerce Platform Activities (EPA) of consumers, enticing them to search, browse and buy products. The frequency and timing of SMA are expected to affect levels of EPA, increasing the number of brand related queries, clickthrough, and purchase orders. This paper applies cross-sectional data analysis to explore such beliefs and demonstrates weak-to-moderate correlations between daily SMA and EPA volumes. Further correlation analysis, using 30-day rolling windows, shows a high variability in correlation of SMA-EPA pairs and calls into question the predictive potential of SMA in relation to EPA. Considering the moderate correlation of selected SMA and EPA pairs (e.g., Post-Orders), we investigate whether SMA features can predict changes in the EPA levels, instead of precise EPA daily volumes. We define such levels in terms of EPA distribution quantiles (2, 3, and 5 levels) over training data. We formulate the EPA quantile predictions as a multi-class categorization problem. The experiments with Random Forest and Logistic Regression show a varied success, performing better than random for the top quantiles of purchase orders and for the lowest quantile of search and clickthrough activities. Similar results are obtained when predicting multi-day cumulative EPA levels (1, 3, and 7 days). Our results have considerable practical implications but, most importantly, urge the common beliefs to be re-examined, seeking a stronger evidence of SMA effects on EPA.

Improvements of entity-relationship (E-R) search techniques have been hampered by a lack of test collections, particularly for complex queries involving multiple entities and relationships. In this paper we describe a method for generating E-R test queries to support comprehensive E-R search experiments. Queries and relevance judgments are created from content that exists in a tabular form where columns represent entity types and the table structure implies one or more relationships among the entities. Editorial work involves creating natural language queries based on relationships represented by the entries in the table. We have publicly released the RELink test collection comprising 600 queries and relevance judgments obtained from a sample of Wikipedia List-of-lists-of-lists tables. The latter comprise tuples of entities that are extracted from columns and labelled by corresponding entity types and relationships they represent. In order to facilitate research in complex E-R retrieval, we have created and released as open source the RELink Framework that includes Apache Lucene indexing and search specifically tailored to E-R retrieval. RELink includes entity and relationship indexing based on the ClueWeb-09-B Web collection with FACC1 text span annotations linked to Wikipedia entities. With ready to use search resources and a comprehensive test collection, we support community in pursuing E-R research at scale.