Robust Design and Evaluation of Predictive Algorithms under Unobserved Confounding

• URL: http://arxiv.org/abs/2212.09844v6
• Date: Wed, 05 Nov 2025 23:30:56 GMT
• Title: Robust Design and Evaluation of Predictive Algorithms under Unobserved Confounding
• Authors: Ashesh Rambachan, Amanda Coston, Edward Kennedy,
• Abstract summary: We propose a framework for robust design and evaluation of predictive algorithms.<n>We show that varying confounding assumptions substantially affects credit risk predictions and fairness evaluations across income groups.
• Score: 6.925076885159747
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predictive algorithms inform consequential decisions in settings with selective labels: outcomes are observed only for units selected by past decision makers. This creates an identification problem under unobserved confounding -- when selected and unselected units differ in unobserved ways that affect outcomes. We propose a framework for robust design and evaluation of predictive algorithms that bounds how much outcomes may differ between selected and unselected units with the same observed characteristics. These bounds formalize common empirical strategies including proxy outcomes and instrumental variables. Our estimators work across bounding strategies and performance measures such as conditional likelihoods, mean square error, and true/false positive rates. Using administrative data from a large Australian financial institution, we show that varying confounding assumptions substantially affects credit risk predictions and fairness evaluations across income groups.

Related papers

• Does Algorithmic Uncertainty Sway Human Experts? Evidence from a Field Experiment in Selective College Admissions [16.423278179819288]
  We define algorithmic reliance as the extent to which a decision outcome depends on whether a more favorable versus less favorable algorithmic prediction is presented to the decision-maker.<n>We show that presenting a more favorable score does not meaningfully increase an applicant's probability of admission on average, even when the models disagree substantially.<n>These findings suggest that, in this expert, high-stakes setting, human decision-making is largely invariant to arbitrary variation in algorithmic predictions.
  arXiv  Detail & Related papers  (2026-01-30T19:03:30Z)
• Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models [58.198220611190884]
  We investigate the impact of decoding strategies on uncertainty estimation in Large Language Models (LLMs)<n>Our experiments show that Contrastive Search, which mitigates repetition, yields better uncertainty estimates on average across a range of preference-aligned LLMs.
  arXiv  Detail & Related papers  (2025-09-20T13:48:13Z)
• A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding [68.43987626137512]
  We propose a principled framework for randomized decision-making based on interval estimates of the quality of each item.<n>We introduce MERIT, an optimization-based method that maximizes the worst-case expected number of top candidates selected.<n>We prove that MERIT satisfies desirable axiomatic properties not guaranteed by existing approaches.
  arXiv  Detail & Related papers  (2025-06-23T19:59:30Z)
• Conformalized Decision Risk Assessment [5.391713612899277]
  We introduce CREDO, a novel framework that quantifies for any candidate decision, a distribution-free upper bound on the probability that the decision is suboptimal.<n>By combining inverse optimization geometry with conformal prediction and generative modeling, CREDO produces risk certificates that are both statistically rigorous and practically interpretable.
  arXiv  Detail & Related papers  (2025-05-19T15:24:38Z)
• Conformal Prediction and Human Decision Making [24.565425060007474]
  Methods to quantify uncertainty in predictions from arbitrary models are in demand in high-stakes domains like medicine and finance. Conformal prediction has emerged as a popular method for producing a set of predictions with specified average coverage. However, the value of conformal prediction sets to assist human decisions remains elusive due to the murky relationship between coverage guarantees and decision makers' goals and strategies.
  arXiv  Detail & Related papers  (2025-03-12T18:18:09Z)
• Calibrated Probabilistic Forecasts for Arbitrary Sequences [58.54729945445505]
  Real-world data streams can change unpredictably due to distribution shifts, feedback loops and adversarial actors. We present a forecasting framework ensuring valid uncertainty estimates regardless of how data evolves.
  arXiv  Detail & Related papers  (2024-09-27T21:46:42Z)
• Quantifying Uncertainty in Deep Learning Classification with Noise in Discrete Inputs for Risk-Based Decision Making [1.529943343419486]
  We propose a mathematical framework to quantify prediction uncertainty for Deep Neural Network (DNN) models. The prediction uncertainty arises from errors in predictors that follow some known finite discrete distribution. Our proposed framework can support risk-based decision making in applications when discrete errors in predictors are present.
  arXiv  Detail & Related papers  (2023-10-09T19:26:24Z)
• Quantification of Predictive Uncertainty via Inference-Time Sampling [57.749601811982096]
  We propose a post-hoc sampling strategy for estimating predictive uncertainty accounting for data ambiguity. The method can generate different plausible outputs for a given input and does not assume parametric forms of predictive distributions.
  arXiv  Detail & Related papers  (2023-08-03T12:43:21Z)
• In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation [92.51773744318119]
  This paper empirically investigates the strengths and weaknesses of different model selection criteria. We highlight that there is a complex interplay between selection strategies, candidate estimators and the data used for comparing them.
  arXiv  Detail & Related papers  (2023-02-06T16:55:37Z)
• Multi-Target Decision Making under Conditions of Severe Uncertainty [0.0]
  We show how incomplete preferential and probabilistic information can be exploited to compare decisions among different targets. We discuss some interesting properties of the proposed orders between decision options and show how they can be concretely computed by linear optimization. We conclude the paper by demonstrating our framework in the context of comparing algorithms under different performance measures.
  arXiv  Detail & Related papers  (2022-12-13T11:47:02Z)
• Explainability's Gain is Optimality's Loss? -- How Explanations Bias Decision-making [0.0]
  Explanations help to facilitate communication between the algorithm and the human decision-maker. Feature-based explanations' semantics of causal models induce leakage from the decision-maker's prior beliefs. Such differences can lead to sub-optimal and biased decision outcomes.
  arXiv  Detail & Related papers  (2022-06-17T11:43:42Z)
• Uncertainty estimation of pedestrian future trajectory using Bayesian approximation [137.00426219455116]
  Under dynamic traffic scenarios, planning based on deterministic predictions is not trustworthy. The authors propose to quantify uncertainty during forecasting using approximation which deterministic approaches fail to capture. The effect of dropout weights and long-term prediction on future state uncertainty has been studied.
  arXiv  Detail & Related papers  (2022-05-04T04:23:38Z)
• A Study on Mitigating Hard Boundaries of Decision-Tree-based Uncertainty Estimates for AI Models [0.0]
  Uncertainty wrappers use a decision tree approach to cluster input quality related uncertainties, assigning inputs strictly to distinct uncertainty clusters. Our objective is to replace this with an approach that mitigates hard decision boundaries while preserving interpretability, runtime complexity, and prediction performance.
  arXiv  Detail & Related papers  (2022-01-10T10:29:12Z)
• On the Fairness of Machine-Assisted Human Decisions [3.4069627091757178]
  We show that the inclusion of a biased human decision-maker can revert common relationships between the structure of the algorithm and the qualities of resulting decisions. In the lab experiment, we demonstrate how predictions informed by gender-specific information can reduce average gender disparities in decisions.
  arXiv  Detail & Related papers  (2021-10-28T17:24:45Z)
• Dense Uncertainty Estimation [62.23555922631451]
  In this paper, we investigate neural networks and uncertainty estimation techniques to achieve both accurate deterministic prediction and reliable uncertainty estimation. We work on two types of uncertainty estimations solutions, namely ensemble based methods and generative model based methods, and explain their pros and cons while using them in fully/semi/weakly-supervised framework.
  arXiv  Detail & Related papers  (2021-10-13T01:23:48Z)
• Information Theoretic Measures for Fairness-aware Feature Selection [27.06618125828978]
  We develop a framework for fairness-aware feature selection, based on information theoretic measures for the accuracy and discriminatory impacts of features. Specifically, our goal is to design a fairness utility score for each feature which quantifies how this feature influences accurate as well as nondiscriminatory decisions.
  arXiv  Detail & Related papers  (2021-06-01T20:11:54Z)
• Characterizing Fairness Over the Set of Good Models Under Selective Labels [69.64662540443162]
  We develop a framework for characterizing predictive fairness properties over the set of models that deliver similar overall performance. We provide tractable algorithms to compute the range of attainable group-level predictive disparities. We extend our framework to address the empirically relevant challenge of selectively labelled data.
  arXiv  Detail & Related papers  (2021-01-02T02:11:37Z)
• Counterfactual Predictions under Runtime Confounding [74.90756694584839]
  We study the counterfactual prediction task in the setting where all relevant factors are captured in the historical data. We propose a doubly-robust procedure for learning counterfactual prediction models in this setting.
  arXiv  Detail & Related papers  (2020-06-30T15:49:05Z)
• Fast, Optimal, and Targeted Predictions using Parametrized Decision Analysis [0.0]
  We develop a class of parametrized actions for Bayesian decision analysis that produce optimal, scalable, and simple targeted predictions. Predictions are constructed for physical activity data from the National Health and Nutrition Examination Survey.
  arXiv  Detail & Related papers  (2020-06-23T15:55:47Z)
• Learning Overlapping Representations for the Estimation of Individualized Treatment Effects [97.42686600929211]
  Estimating the likely outcome of alternatives from observational data is a challenging problem. We show that algorithms that learn domain-invariant representations of inputs are often inappropriate. We develop a deep kernel regression algorithm and posterior regularization framework that substantially outperforms the state-of-the-art on a variety of benchmarks data sets.
  arXiv  Detail & Related papers  (2020-01-14T12:56:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.