Leveraging Multisource Heterogeneous Data for Financial Risk Prediction: A Novel Hybrid-Strategy-Based Self-Adaptive Method

In stock

Publication History

Received: February 15, 2019
Revised: October 26, 2019; August 19, 2020; November 13, 2020
Accepted: November 28, 2020
Published online: October 14, 2021


Downloadable File
Emerging phenomena of ubiquitous multisource data provide promising avenues for making breakthroughs in financial risk prediction. While most existing methods for financial risk prediction are based on a single information source, which may not adequately capture various complex factors that jointly influence financial risks, we propose a hybrid-strategy-based self-adaptive method to effectively leverage heterogeneous soft information drawn from a variety of sources. The method uses a proposed new feature, sparsity learning method, to adaptively integrate multisource heterogeneous soft features with hard features and a proposed improved evidential reasoning rule to adaptively aggregate base classifier predictions, thereby alleviating both the declarative bias and the procedural bias of the learning process. Evaluation in two cases at the individual level (concerning borrowers at a P2P lending platform) and the company level (concerning listed companies in the Chinese stock market) showed that, compared with relying solely on hard features, effectively incorporating multisource heterogeneous soft features using our proposed method enabled earlier prediction of financial risks with desirable performance.
Additional Details
Author Gang Wang, Gang Chen, Huimin Zhao, Feng Zhang, Shanlin Yang, and Tian Lu
Year 2021
Volume 45
Issue 4
Keywords Financial risk prediction, soft information, ensemble learning, hybrid learning strategy, adaptive integration, adaptive aggregation
Page Numbers 1949-1998; DOI: 10.25300/MISQ/2021/16118
Copyright © 2023 MISQ. All rights reserved.