Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction

TL;DR

This paper introduces a novel causal feature distillation approach for risk prediction that enhances interpretability, precision, and recall by transforming features into causal attributions tailored to the specific task.

Contribution

The proposed TDCFD model uniquely combines causal feature attribution with deep learning to improve trustworthiness and interpretability in risk prediction models.

Findings

Outperforms state-of-the-art methods in precision and recall

Enhances interpretability through causal feature attributions

Demonstrates effectiveness on synthetic and real datasets

Abstract

Since artificial intelligence has seen tremendous recent successes in many areas, it has sparked great interest in its potential for trustworthy and interpretable risk prediction. However, most models lack causal reasoning and struggle with class imbalance, leading to poor precision and recall. To address this, we propose a Task-Driven Causal Feature Distillation model (TDCFD) to transform original feature values into causal feature attributions for the specific risk prediction task. The causal feature attribution helps describe how much contribution the value of this feature can make to the risk prediction result. After the causal feature distillation, a deep neural network is applied to produce trustworthy prediction results with causal interpretability and high precision/recall. We evaluate the performance of our TDCFD method on several synthetic and real datasets, and the results demonstrate its superiority over the state-of-the-art methods regarding precision, recall, interpretability, and causality.