Counterfactual Explanation for Multivariate Time Series Forecasting with Exogenous Variables
This addresses interpretability issues in black-box models for time series forecasting, particularly in domains like business and marketing, but is incremental as it builds on existing counterfactual explanation techniques.
The study tackled the problem of generating counterfactual explanations for time series forecasting with exogenous variables, proposing a method that was validated through theoretical analysis and empirical experiments to show accuracy and practical applicability.
Currently, machine learning is widely used across various domains, including time series data analysis. However, some machine learning models function as black boxes, making interpretability a critical concern. One approach to address this issue is counterfactual explanation (CE), which aims to provide insights into model predictions. This study focuses on the relatively underexplored problem of generating counterfactual explanations for time series forecasting. We propose a method for extracting CEs in time series forecasting using exogenous variables, which are frequently encountered in fields such as business and marketing. In addition, we present methods for analyzing the influence of each variable over an entire time series, generating CEs by altering only specific variables, and evaluating the quality of the resulting CEs. We validate the proposed method through theoretical analysis and empirical experiments, showcasing its accuracy and practical applicability. These contributions are expected to support real-world decision-making based on time series data analysis.