No $D_{\text{train}}$: Model-Agnostic Counterfactual Explanations Using Reinforcement Learning

TL;DR

This paper introduces NTD-CFE, a reinforcement learning-based, model-agnostic method for generating counterfactual explanations for ML models, especially effective when training data is unavailable, applicable to static and multivariate time-series.

Contribution

NTD-CFE is the first model-agnostic counterfactual explanation method that operates without training data and handles multivariate time-series using reinforcement learning.

Findings

NTD-CFE produces fewer and smaller changes in counterfactuals.

It outperforms four baseline methods on multiple datasets.

CFEs generated are more actionable due to reduced change magnitude.

Abstract

Machine learning (ML) methods have experienced significant growth in the past decade, yet their practical application in high-impact real-world domains has been hindered by their opacity. When ML methods are responsible for making critical decisions, stakeholders often require insights into how to alter these decisions. Counterfactual explanations (CFEs) have emerged as a solution, offering interpretations of opaque ML models and providing a pathway to transition from one decision to another. However, most existing CFE methods require access to the model's training dataset, few methods can handle multivariate time-series, and none of model-agnostic CFE methods can handle multivariate time-series without training datasets. These limitations can be formidable in many scenarios. In this paper, we present NTD-CFE, a novel model-agnostic CFE method based on reinforcement learning (RL) that generates CFEs when training datasets are unavailable. NTD-CFE is suitable for both static and multivariate time-series datasets with continuous and discrete features. NTD-CFE reduces the CFE search space from a multivariate time-series domain to a lower dimensional space and addresses the problem using RL. Users have the flexibility to specify non-actionable, immutable, and preferred features, as well as causal constraints. We demonstrate the performance of NTD-CFE against four baselines on several datasets and find that, despite not having access to a training dataset, NTD-CFE finds CFEs that make significantly fewer and significantly smaller changes to the input time-series. These properties make CFEs more actionable, as the magnitude of change required to alter an outcome is vastly reduced. The code is available in the supplementary material.