Rayid Ghani

Kasun Amarasinghe, Kit T. Rodolfa, Sérgio Jesus et al. · cmu

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, resulting in limited conclusions of methods' real-world utility. In this work, we seek to bridge this gap by conducting a study that evaluates three popular explainable ML methods in a setting consistent with the intended deployment context. We build on a previous study on e-commerce fraud detection and make crucial modifications to its setup relaxing the simplifying assumptions made in the original work that departed from the deployment context. In doing so, we draw drastically different conclusions from the earlier work and find no evidence for the incremental utility of the tested methods in the task. Our results highlight how seemingly trivial experimental design choices can yield misleading conclusions, with lessons about the necessity of not only evaluating explainable ML methods using tasks, data, users, and metrics grounded in the intended deployment contexts but also developing methods tailored to specific applications. In addition, we believe the design of this experiment can serve as a template for future study designs evaluating explainable ML methods in other real-world contexts.

Rachel M. Kim, Blaine Kuehnert, Alice Lai et al.

As Artificial Intelligence (AI) systems proliferate, the need for systematic, transparent, and actionable processes for evaluating them is growing. While many resources exist to support AI evaluation, they have several limitations. Few address both the process of designing, developing, and deploying an AI system and the outcomes it produces. Furthermore, few are end-to-end and operational, give actionable guidance, or present evidence of usability or effectiveness in practice. In this paper, we introduce a third-party AI assurance framework that addresses these gaps. We focus on third-party assurance to prevent conflict of interest and ensure credibility and accountability of the process. We begin by distinguishing assurance from audits in several key dimensions. Then, following design principles, we reflect on the shortcomings of existing resources to identify a set of design requirements for AI assurance. We then construct a prototype of an assurance process that consists of (1) a responsibility assignment matrix to determine the different levels of involvement each stakeholder has at each stage of the AI lifecycle, (2) an interview protocol for each stakeholder of an AI system, (3) a maturity matrix to assess AI systems' adherence to best practices, and (4) a template for an assurance report that draws from more mature assurance practices in business accounting. We conduct early validation of our AI assurance framework by applying the framework to two distinct AI use cases -- a business document tagging tool for downstream processing in a large private firm, and a housing resource allocation tool in a public agency -- and conducting six expert validation interviews. Our findings show early evidence that our AI assurance framework is sound and comprehensive, usable across different organizational contexts, and effective at identifying bespoke issues with AI systems.

Emily Black, Rakshit Naidu, Rayid Ghani et al.

While algorithmic fairness is a thriving area of research, in practice, mitigating issues of bias often gets reduced to enforcing an arbitrarily chosen fairness metric, either by enforcing fairness constraints during the optimization step, post-processing model outputs, or by manipulating the training data. Recent work has called on the ML community to take a more holistic approach to tackle fairness issues by systematically investigating the many design choices made through the ML pipeline, and identifying interventions that target the issue's root cause, as opposed to its symptoms. While we share the conviction that this pipeline-based approach is the most appropriate for combating algorithmic unfairness on the ground, we believe there are currently very few methods of \emph{operationalizing} this approach in practice. Drawing on our experience as educators and practitioners, we first demonstrate that without clear guidelines and toolkits, even individuals with specialized ML knowledge find it challenging to hypothesize how various design choices influence model behavior. We then consult the fair-ML literature to understand the progress to date toward operationalizing the pipeline-aware approach: we systematically collect and organize the prior work that attempts to detect, measure, and mitigate various sources of unfairness through the ML pipeline. We utilize this extensive categorization of previous contributions to sketch a research agenda for the community. We hope this work serves as the stepping stone toward a more comprehensive set of resources for ML researchers, practitioners, and students interested in exploring, designing, and testing pipeline-oriented approaches to algorithmic fairness.

Oscar Giles, Kasra Hosseini, Grigorios Mingas et al.

Synthetic datasets are often presented as a silver-bullet solution to the problem of privacy-preserving data publishing. However, for many applications, synthetic data has been shown to have limited utility when used to train predictive models. One promising potential application of these data is in the exploratory phase of the machine learning workflow, which involves understanding, engineering and selecting features. This phase often involves considerable time, and depends on the availability of data. There would be substantial value in synthetic data that permitted these steps to be carried out while, for example, data access was being negotiated, or with fewer information governance restrictions. This paper presents an empirical analysis of the agreement between the feature importance obtained from raw and from synthetic data, on a range of artificially generated and real-world datasets (where feature importance represents how useful each feature is when predicting a the outcome). We employ two differentially-private methods to produce synthetic data, and apply various utility measures to quantify the agreement in feature importance as this varies with the level of privacy. Our results indicate that synthetic data can sometimes preserve several representations of the ranking of feature importance in simple settings but their performance is not consistent and depends upon a number of factors. Particular caution should be exercised in more nuanced real-world settings, where synthetic data can lead to differences in ranked feature importance that could alter key modelling decisions. This work has important implications for developing synthetic versions of highly sensitive data sets in fields such as finance and healthcare.

Ka Ho Brian Chor, Kit T. Rodolfa, Rayid Ghani

Human services systems make key decisions that impact individuals in the society. The U.S. child welfare system makes such decisions, from screening-in hotline reports of suspected abuse or neglect for child protective investigations, placing children in foster care, to returning children to permanent home settings. These complex and impactful decisions on children's lives rely on the judgment of child welfare decisionmakers. Child welfare agencies have been exploring ways to support these decisions with empirical, data-informed methods that include machine learning (ML). This paper describes a conceptual framework for ML to support child welfare decisions. The ML framework guides how child welfare agencies might conceptualize a target problem that ML can solve; vet available administrative data for building ML; formulate and develop ML specifications that mirror relevant populations and interventions the agencies are undertaking; deploy, evaluate, and monitor ML as child welfare context, policy, and practice change over time. Ethical considerations, stakeholder engagement, and avoidance of common pitfalls underpin the framework's impact and success. From abstract to concrete, we describe one application of this framework to support a child welfare decision. This ML framework, though child welfare-focused, is generalizable to solving other public policy problems.

Sérgio Jesus, Pedro Saleiro, Inês Oliveira e Silva et al.

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.

Pedro Saleiro, Benedict Kuester, Loren Hinkson et al.

Recent work has raised concerns on the risk of unintended bias in AI systems being used nowadays that can affect individuals unfairly based on race, gender or religion, among other possible characteristics. While a lot of bias metrics and fairness definitions have been proposed in recent years, there is no consensus on which metric/definition should be used and there are very few available resources to operationalize them. Therefore, despite recent awareness, auditing for bias and fairness when developing and deploying AI systems is not yet a standard practice. We present Aequitas, an open source bias and fairness audit toolkit that is an intuitive and easy to use addition to the machine learning workflow, enabling users to seamlessly test models for several bias and fairness metrics in relation to multiple population sub-groups. Aequitas facilitates informed and equitable decisions around developing and deploying algorithmic decision making systems for both data scientists, machine learning researchers and policymakers.

Kit T. Rodolfa, Erika Salomon, Jin Yao et al.

Many incarcerated individuals face significant and complex challenges, including mental illness, substance dependence, and homelessness, yet jails and prisons are often poorly equipped to address these needs. With little support from the existing criminal justice system, these needs can remain untreated and worsen, often leading to further offenses and a cycle of incarceration with adverse outcomes both for the individual and for public safety, with particularly large impacts on communities of color that continue to widen the already extensive racial disparities in criminal justice outcomes. Responding to these failures, a growing number of criminal justice stakeholders are seeking to break this cycle through innovative approaches such as community-driven and alternative approaches to policing, mentoring, community building, restorative justice, pretrial diversion, holistic defense, and social service connections. Here we report on a collaboration between Johnson County, Kansas, and Carnegie Mellon University to perform targeted, proactive mental health outreach in an effort to reduce reincarceration rates. This paper describes the data used, our predictive modeling approach and results, as well as the design and analysis of a field trial conducted to confirm our model's predictive power, evaluate the impact of this targeted outreach, and understand at what level of reincarceration risk outreach might be most effective. Through this trial, we find that our model is highly predictive of new jail bookings, with more than half of individuals in the trial's highest-risk group returning to jail in the following year. Outreach was most effective among these highest-risk individuals, with impacts on mental health utilization, EMS dispatches, and criminal justice involvement.

Jacob Emmerson, Rayid Ghani, Zheyuan Ryan Shi

Artificial Intelligence for Social Good (AI4SG) is an emerging effort that aims to address complex societal challenges with the powerful capabilities of AI systems. These challenges range from local issues with transit networks to global wildlife preservation. However, regardless of scale, a critical bottleneck for many AI4SG initiatives is the laborious process of problem scoping -- a complex and resource-intensive task -- due to a scarcity of professionals with both technical and domain expertise. Given the remarkable applications of large language models (LLM), we propose a Problem Scoping Agent (PSA) that uses an LLM to generate comprehensive project proposals grounded in scientific literature and real-world knowledge. We demonstrate that our PSA framework generates proposals comparable to those written by experts through a blind review and AI evaluations. Finally, we document the challenges of real-world problem scoping and note several areas for future work.

Catalina Vajiac, Arun Frey, Joachim Baumann et al.

Rental assistance programs provide individuals with financial assistance to prevent housing instabilities caused by evictions and avert homelessness. Since these programs operate under resource constraints, they must decide who to prioritize. Typically, funding is distributed by a reactive or first-come-first serve allocation process that does not systematically consider risk of future homelessness. We partnered with Allegheny County, PA to explore a proactive allocation approach that prioritizes individuals facing eviction based on their risk of future homelessness. Our ML system that uses state and county administrative data to accurately identify individuals in need of support outperforms simpler prioritization approaches by at least 20% while being fair and equitable across race and gender. Furthermore, our approach would identify 28% of individuals who are overlooked by the current process and end up homeless. Beyond improvements to the rental assistance program in Allegheny County, this study can inform the development of evidence-based decision support tools in similar contexts, including lessons about data needs, model design, evaluation, and field validation.

Hemank Lamba, Kit T. Rodolfa, Rayid Ghani

Applications of machine learning (ML) to high-stakes policy settings -- such as education, criminal justice, healthcare, and social service delivery -- have grown rapidly in recent years, sparking important conversations about how to ensure fair outcomes from these systems. The machine learning research community has responded to this challenge with a wide array of proposed fairness-enhancing strategies for ML models, but despite the large number of methods that have been developed, little empirical work exists evaluating these methods in real-world settings. Here, we seek to fill this research gap by investigating the performance of several methods that operate at different points in the ML pipeline across four real-world public policy and social good problems. Across these problems, we find a wide degree of variability and inconsistency in the ability of many of these methods to improve model fairness, but post-processing by choosing group-specific score thresholds consistently removes disparities, with important implications for both the ML research community and practitioners deploying machine learning to inform consequential policy decisions.

Kit T. Rodolfa, Hemank Lamba, Rayid Ghani

Growing use of machine learning in policy and social impact settings have raised concerns for fairness implications, especially for racial minorities. These concerns have generated considerable interest among machine learning and artificial intelligence researchers, who have developed new methods and established theoretical bounds for improving fairness, focusing on the source data, regularization and model training, or post-hoc adjustments to model scores. However, little work has studied the practical trade-offs between fairness and accuracy in real-world settings to understand how these bounds and methods translate into policy choices and impact on society. Our empirical study fills this gap by investigating the impact of mitigating disparities on accuracy, focusing on the common context of using machine learning to inform benefit allocation in resource-constrained programs across education, mental health, criminal justice, and housing safety. Here we describe applied work in which we find fairness-accuracy trade-offs to be negligible in practice. In each setting studied, explicitly focusing on achieving equity and using our proposed post-hoc disparity mitigation methods, fairness was substantially improved without sacrificing accuracy. This observation was robust across policy contexts studied, scale of resources available for intervention, time, and relative size of the protected groups. These empirical results challenge a commonly held assumption that reducing disparities either requires accepting an appreciable drop in accuracy or the development of novel, complex methods, making reducing disparities in these applications more practical.

Kasun Amarasinghe, Kit Rodolfa, Hemank Lamba et al.

Explainability is highly-desired in Machine Learning (ML) systems supporting high-stakes policy decisions in areas such as health, criminal justice, education, and employment. While the field of explainable ML has expanded in recent years, much of this work has not taken real-world needs into account. A majority of proposed methods are designed with \textit{generic} explainability goals without well-defined use-cases or intended end-users and evaluated on simplified tasks, benchmark problems/datasets, or with proxy users (e.g., AMT). We argue that these simplified evaluation settings do not capture the nuances and complexities of real-world applications. As a result, the applicability and effectiveness of this large body of theoretical and methodological work in real-world applications are unclear. In this work, we take steps toward addressing this gap for the domain of public policy. First, we identify the primary use-cases of explainable ML within public policy problems. For each use case, we define the end-users of explanations and the specific goals the explanations have to fulfill. Finally, we map existing work in explainable ML to these use-cases, identify gaps in established capabilities, and propose research directions to fill those gaps to have a practical societal impact through ML. The contribution is 1) a methodology for explainable ML researchers to identify use cases and develop methods targeted at them and 2) using that methodology for the domain of public policy and giving an example for the researchers on developing explainable ML methods that result in real-world impact.

Zheyuan Ryan Shi, Zhiwei Steven Wu, Rayid Ghani et al.

Applications of machine learning in the non-profit and public sectors often feature an iterative workflow of data acquisition, prediction, and optimization of interventions. There are four major pain points that a machine learning pipeline must overcome in order to be actually useful in these settings: small data, data collected only under the default intervention, unmodeled objectives due to communication gap, and unforeseen consequences of the intervention. In this paper, we introduce bandit data-driven optimization, the first iterative prediction-prescription framework to address these pain points. Bandit data-driven optimization combines the advantages of online bandit learning and offline predictive analytics in an integrated framework. We propose PROOF, a novel algorithm for this framework and formally prove that it has no-regret. Using numerical simulations, we show that PROOF achieves superior performance than existing baseline. We also apply PROOF in a detailed case study of food rescue volunteer recommendation, and show that PROOF as a framework works well with the intricacies of ML models in real-world AI for non-profit and public sector applications.

Harrison Wilde, Lucia Lushi Chen, Austin Nguyen et al.

Rough sleeping is a chronic problem faced by some of the most disadvantaged people in modern society. This paper describes work carried out in partnership with Homeless Link, a UK-based charity, in developing a data-driven approach to assess the quality of incoming alerts from members of the public aimed at connecting people sleeping rough on the streets with outreach service providers. Alerts are prioritised based on the predicted likelihood of successfully connecting with the rough sleeper, helping to address capacity limitations and to quickly, effectively, and equitably process all of the alerts that they receive. Initial evaluation concludes that our approach increases the rate at which rough sleepers are found following a referral by at least 15\% based on labelled data, implying a greater overall increase when the alerts with unknown outcomes are considered, and suggesting the benefit in a trial taking place over a longer period to assess the models in practice. The discussion and modelling process is done with careful considerations of ethics, transparency and explainability due to the sensitive nature of the data in this context and the vulnerability of the people that are affected.

Avishek Kumar, Arthi Ramachandran, Adolfo De Unanue et al.

Retaining persons living with HIV (PLWH) in medical care is paramount to preventing new transmissions of the virus and allowing PLWH to live normal and healthy lifespans. Maintaining regular appointments with an HIV provider and taking medication daily for a lifetime is exceedingly difficult. 51% of PLWH are non-adherent with their medications and eventually drop out of medical care. Current methods of re-linking individuals to care are reactive (after a patient has dropped-out) and hence not very effective. We describe our system to predict who is most at risk to drop-out-of-care for use by the University of Chicago HIV clinic and the Chicago Department of Public Health. Models were selected based on their predictive performance under resource constraints, stability over time, as well as fairness. Our system is applicable as a point-of-care system in a clinical setting as well as a batch prediction system to support regular interventions at the city level. Our model performs 3x better than the baseline for the clinical model and 2.3x better than baseline for the city-wide model. The code has been released on github and we hope this methodology, particularly our focus on fairness, will be adopted by other clinics and public health agencies in order to curb the HIV epidemic.

Kit T. Rodolfa, Erika Salomon, Lauren Haynes et al.

The criminal justice system is currently ill-equipped to improve outcomes of individuals who cycle in and out of the system with a series of misdemeanor offenses. Often due to constraints of caseload and poor record linkage, prior interactions with an individual may not be considered when an individual comes back into the system, let alone in a proactive manner through the application of diversion programs. The Los Angeles City Attorney's Office recently created a new Recidivism Reduction and Drug Diversion unit (R2D2) tasked with reducing recidivism in this population. Here we describe a collaboration with this new unit as a case study for the incorporation of predictive equity into machine learning based decision making in a resource-constrained setting. The program seeks to improve outcomes by developing individually-tailored social service interventions (i.e., diversions, conditional plea agreements, stayed sentencing, or other favorable case disposition based on appropriate social service linkage rather than traditional sentencing methods) for individuals likely to experience subsequent interactions with the criminal justice system, a time and resource-intensive undertaking that necessitates an ability to focus resources on individuals most likely to be involved in a future case. Seeking to achieve both efficiency (through predictive accuracy) and equity (improving outcomes in traditionally under-served communities and working to mitigate existing disparities in criminal justice outcomes), we discuss the equity outcomes we seek to achieve, describe the corresponding choice of a metric for measuring predictive fairness in this context, and explore a set of options for balancing equity and efficiency when building and selecting machine learning models in an operational public policy setting.

Kit T Rodolfa, Adolfo De Unanue, Matt Gee et al.

Like medicine, psychology, or education, data science is fundamentally an applied discipline, with most students who receive advanced degrees in the field going on to work on practical problems. Unlike these disciplines, however, data science education remains heavily focused on theory and methods, and practical coursework typically revolves around cleaned or simplified data sets that have little analog in professional applications. We believe that the environment in which new data scientists are trained should more accurately reflect that in which they will eventually practice and propose here a data science master's degree program that takes inspiration from the residency model used in medicine. Students in the suggested program would spend three years working on a practical problem with an industry, government, or nonprofit partner, supplemented with coursework in data science methods and theory. We also discuss how this program can also be implemented in shorter formats to augment existing professional masters programs in different disciplines. This approach to learning by doing is designed to fill gaps in our current approach to data science education and ensure that students develop the skills they need to practice data science in a professional context and under the many constraints imposed by that context.

Sebastian Vollmer, Bilal A. Mateen, Gergo Bohner et al.

Machine learning (ML), artificial intelligence (AI) and other modern statistical methods are providing new opportunities to operationalize previously untapped and rapidly growing sources of data for patient benefit. Whilst there is a lot of promising research currently being undertaken, the literature as a whole lacks: transparency; clear reporting to facilitate replicability; exploration for potential ethical concerns; and, clear demonstrations of effectiveness. There are many reasons for why these issues exist, but one of the most important that we provide a preliminary solution for here is the current lack of ML/AI- specific best practice guidance. Although there is no consensus on what best practice looks in this field, we believe that interdisciplinary groups pursuing research and impact projects in the ML/AI for health domain would benefit from answering a series of questions based on the important issues that exist when undertaking work of this nature. Here we present 20 questions that span the entire project life cycle, from inception, data analysis, and model evaluation, to implementation, as a means to facilitate project planning and post-hoc (structured) independent evaluation. By beginning to answer these questions in different settings, we can start to understand what constitutes a good answer, and we expect that the resulting discussion will be central to developing an international consensus framework for transparent, replicable, ethical and effective research in artificial intelligence (AI-TREE) for health.