CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactuals
This addresses the need for accurate counterfactual inference in fields like finance, healthcare, and marketing, though it is incremental as it adapts existing autoencoder methods to a time series setting.
The paper tackled the problem of counterfactual inference for time series data impacted by market events by introducing the Conditional Entropy-Penalized Autoencoder (CEPAE), which generally outperformed other approaches in evaluated metrics on synthetic, semi-synthetic, and real-world datasets.
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 is motivated by an industrial application. Utilizing the abduction-action-prediction procedure and the Structural Causal Model framework, we first adapt methods based on variational autoencoders and adversarial autoencoders, both previously used in counterfactual literature 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 encourage disentangled data representations. We validate our approach both theoretically and experimentally on synthetic, semi-synthetic, and real-world datasets, showing that CEPAE generally outperforms the other approaches in the evaluated metrics.