Causal Interventional Prediction System for Robust and Explainable Effect Forecasting
This work addresses robustness and explainability issues in forecasting systems, which is crucial for reliable AI applications in various domains, though it appears incremental as it builds on existing causal and imputation techniques.
The paper tackled the problem of hidden bias and missing information in AI-based forecasting systems by developing a causal interventional prediction system (CIPS) that uses a variational autoencoder and multiple imputations, achieving superior performance over state-of-the-art methods with demonstrated versatility and extensibility.
Although the widespread use of AI systems in today's world is growing, many current AI systems are found vulnerable due to hidden bias and missing information, especially in the most commonly used forecasting system. In this work, we explore the robustness and explainability of AI-based forecasting systems. We provide an in-depth analysis of the underlying causality involved in the effect prediction task and further establish a causal graph based on treatment, adjustment variable, confounder, and outcome. Correspondingly, we design a causal interventional prediction system (CIPS) based on a variational autoencoder and fully conditional specification of multiple imputations. Extensive results demonstrate the superiority of our system over state-of-the-art methods and show remarkable versatility and extensibility in practice.