Explainable Artificial Intelligence for Economic Time Series: A Comprehensive Review and a Systematic Taxonomy of Methods and Concepts

TL;DR

This comprehensive review categorizes and analyzes explainable AI methods tailored for economic time series, addressing unique challenges like non-stationarity and regime shifts, and linking explainability with causal inference and policy analysis.

Contribution

It introduces a systematic taxonomy of XAI methods for economic time series, including adaptations for temporal dependence and computational efficiency, and connects explainability with causal and policy insights.

Findings

Proposes a taxonomy classifying explanation methods by mechanism and time-series compatibility.

Synthesizes adaptations like Vector SHAP and WindowSHAP for better interpretability and efficiency.

Discusses the integration of explainability with causal inference and policy applications.

Abstract

Explainable Artificial Intelligence (XAI) is increasingly required in computational economics, where machine-learning forecasters can outperform classical econometric models but remain difficult to audit and use for policy. This survey reviews and organizes the growing literature on XAI for economic time series, where autocorrelation, non-stationarity, seasonality, mixed frequencies, and regime shifts can make standard explanation techniques unreliable or economically implausible. We propose a taxonomy that classifies methods by (i) explanation mechanism: propagation-based approaches (e.g., Integrated Gradients, Layer-wise Relevance Propagation), perturbation and game-theoretic attribution (e.g., permutation importance, LIME, SHAP), and function-based global tools (e.g., Accumulated Local Effects); (ii) time-series compatibility, including preservation of temporal dependence, stability over time, and respect for data-generating constraints. We synthesize time-series-specific adaptations such as vector- and window-based formulations (e.g., Vector SHAP, WindowSHAP) that reduce lag fragmentation and computational cost while improving interpretability. We also connect explainability to causal inference and policy analysis through interventional attributions (Causal Shapley values) and constrained counterfactual reasoning. Finally, we discuss intrinsically interpretable architectures (notably attention-based transformers) and provide guidance for decision-grade applications such as nowcasting, stress testing, and regime monitoring, emphasizing attribution uncertainty and explanation dynamics as indicators of structural change.