Impact of mortgage soft information in loan pricing on default prediction using machine learning

IF 1.8 4区经济学 Q2 BUSINESS, FINANCE

International Review of Finance Pub Date : 2022-09-18 DOI:10.1111/irfi.12392

Thi Mai Luong, Harald Scheule, Nitya Wanzare

引用次数: 1

Abstract

We analyze the impact of soft information on US mortgages for default prediction and provide a new measure for lender soft information that is based on the interest rates offered to borrowers and incremental to public hard information. Hard and soft information provide for a variation in annual default probabilities of approximately 3%. Soft information has a lesser impact over time and time since origination. Lenders rely more on soft information for high-risk borrowers. Our study evidences the importance of soft information collected at loan origination.

Abstract Image

查看原文本刊更多论文

贷款定价中抵押贷款软信息对机器学习违约预测的影响

我们分析了软信息对美国抵押贷款违约预测的影响，并提供了一种基于向借款人提供的利率和公共硬信息增量的贷方软信息的新措施。硬数据和软数据显示，年违约概率的变化幅度约为3%。随着时间的推移，软信息的影响会越来越小。对于高风险借款人，贷款机构更多地依赖软信息。我们的研究证明了贷款发起时收集的软信息的重要性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Review of Finance BUSINESS, FINANCE-

CiteScore

3.30

自引率

5.90%

发文量

期刊介绍： The International Review of Finance (IRF) publishes high-quality research on all aspects of financial economics, including traditional areas such as asset pricing, corporate finance, market microstructure, financial intermediation and regulation, financial econometrics, financial engineering and risk management, as well as new areas such as markets and institutions of emerging market economies, especially those in the Asia-Pacific region. In addition, the Letters Section in IRF is a premium outlet of letter-length research in all fields of finance. The length of the articles in the Letters Section is limited to a maximum of eight journal pages.