A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanations
Abstract: Counterfactual explanations constitute among the most popular methods for analyzing black-box systems since they can recommend cost-efficient and actionable changes to the input of a system to obtain the desired system output. While most of the existing counterfactual methods explain a single instance, several real-world problems, such as customer satisfaction, require the identification of a single counterfactual that can satisfy multiple instances (e.g. customers) simultaneously. To address this limitation, in this work, we propose a flexible two-stage algorithm for finding groups of instances and computing cost-efficient multi-instance counterfactual explanations. The paper presents the algorithm and its performance against popular alternatives through a comparative evaluation.
- Byrne, R.M.J.: Counterfactuals in explainable artificial intelligence (xai): Evidence from human reasoning. In: IJCAI-19. pp. 6276–6282 (7 2019). https://doi.org/10.24963/IJCAI.2019/876
- Guidotti, R.: Counterfactual explanations and how to find them: literature review and benchmarking. Data Mining and Knowledge Discovery pp. 1–55 (2022). https://doi.org/10.1007/s10618-022-00831-6
- IBM: Ibm hr analytics employee. https://www.kaggle.com/pavansubhasht/ibm-hr-analytics-attrition-dataset (2020)
- Molnar, C.: Interpretable Machine Learning (2019)
- Reeves, C.R.: Genetic algorithms. Handbook of metaheuristics pp. 109–139 (2010)
- Wightman, L.F.: Lsac national longitudinal bar passage study. lsac research report series. (1998)
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.