HGV4Risk: Hierarchical Global View-guided Sequence Representation Learning for Risk Prediction

TL;DR

This paper introduces HGV4Risk, a hierarchical global view-guided sequence representation framework that enhances risk prediction accuracy by integrating global graph embeddings and adaptive attention mechanisms, outperforming existing models.

Contribution

The paper proposes a novel end-to-end framework combining global graph embedding and harmonic attention for improved risk prediction from sequence data.

Findings

Achieves superior performance on healthcare risk prediction datasets.

Effectively models temporal correlations and observation significance.

Demonstrates applicability in industrial credit risk scenarios.

Abstract

Risk prediction, as a typical time series modeling problem, is usually achieved by learning trends in markers or historical behavior from sequence data, and has been widely applied in healthcare and finance. In recent years, deep learning models, especially Long Short-Term Memory neural networks (LSTMs), have led to superior performances in such sequence representation learning tasks. Despite that some attention or self-attention based models with time-aware or feature-aware enhanced strategies have achieved better performance compared with other temporal modeling methods, such improvement is limited due to a lack of guidance from global view. To address this issue, we propose a novel end-to-end Hierarchical Global View-guided (HGV) sequence representation learning framework. Specifically, the Global Graph Embedding (GGE) module is proposed to learn sequential clip-aware representations from temporal correlation graph at instance level. Furthermore, following the way of key-query attention, the harmonic $\beta$-attention ($\beta$-Attn) is also developed for making a global trade-off between time-aware decay and observation significance at channel level adaptively. Moreover, the hierarchical representations at both instance level and channel level can be coordinated by the heterogeneous information aggregation under the guidance of global view. Experimental results on a benchmark dataset for healthcare risk prediction, and a real-world industrial scenario for Small and Mid-size Enterprises (SMEs) credit overdue risk prediction in MYBank, Ant Group, have illustrated that the proposed model can achieve competitive prediction performance compared with other known baselines.