TRACER: A Framework for Facilitating Accurate and Interpretable Analytics for High Stakes Applications

TL;DR

TRACER is a versatile framework that enhances the accuracy and interpretability of predictive models in high-stakes domains like healthcare and finance, by capturing both time-invariant and time-variant feature importance.

Contribution

The paper introduces a novel model TITV within the TRACER framework that effectively captures temporal feature importance, improving interpretability without sacrificing accuracy.

Findings

TRACER outperforms existing models in healthcare datasets.

Clinicians validate the interpretability of TRACER at patient and feature levels.

TRACER is effective in finance and temperature forecasting applications.

Abstract

In high stakes applications such as healthcare and finance analytics, the interpretability of predictive models is required and necessary for domain practitioners to trust the predictions. Traditional machine learning models, e.g., logistic regression (LR), are easy to interpret in nature. However, many of these models aggregate time-series data without considering the temporal correlations and variations. Therefore, their performance cannot match up to recurrent neural network (RNN) based models, which are nonetheless difficult to interpret. In this paper, we propose a general framework TRACER to facilitate accurate and interpretable predictions, with a novel model TITV devised for healthcare analytics and other high stakes applications such as financial investment and risk management. Different from LR and other existing RNN-based models, TITV is designed to capture both the time-invariant and the time-variant feature importance using a feature-wise transformation subnetwork and a self-attention subnetwork, for the feature influence shared over the entire time series and the time-related importance respectively. Healthcare analytics is adopted as a driving use case, and we note that the proposed TRACER is also applicable to other domains, e.g., fintech. We evaluate the accuracy of TRACER extensively in two real-world hospital datasets, and our doctors/clinicians further validate the interpretability of TRACER in both the patient level and the feature level. Besides, TRACER is also validated in a high stakes financial application and a critical temperature forecasting application. The experimental results confirm that TRACER facilitates both accurate and interpretable analytics for high stakes applications.