CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals

Abstract

The ability to accurately perform counterfactual inference on time series is crucial for decision-making in fields like finance, healthcare, and marketing, as it allows us to understand the impact of events or treatments on outcomes over time. In this paper, we introduce a new counterfactual inference approach tailored to time series data impacted by market events, which arises from an industrial context. Utilizing the abduction-action-prediction procedure and the Structural Causal Model framework, we begin employing methods based on variational autoencoders and adversarial autoencoders, both previously used in counterfactual works although not in time series settings. Then, we present the Conditional Entropy-Penalized Autoencoder (CEPAE), a novel autoencoder-based approach for counterfactual inference, which employs an entropy penalization loss over the latent space to achieve disentangled data representations. We validate our approach both theoretically and experimentally on synthetic, semi-synthetic, and real-world datasets, showing that CEPAE outperforms the other approaches in the evaluated metrics.