{"title":"Stock price crashes in China: an artificial neural network approach","authors":"Le Wang, Liping Zou, Ji Wu","doi":"10.1108/par-08-2022-0121","DOIUrl":null,"url":null,"abstract":"\nPurpose\nThis paper aims to use artificial neural network (ANN) methods to predict stock price crashes in the Chinese equity market.\n\n\nDesign/methodology/approach\nThree ANN models are developed and compared with the logistic regression model.\n\n\nFindings\nResults from this study conclude that the ANN approaches outperform the traditional logistic regression model, with fewer hidden layers in the ANN model having superior performance compared to the ANNs with multiple hidden layers. Results from the ANN approach also reveal that foreign institutional ownership, financial leverage, weekly average return and market-to-book ratio are the important variables when predicting stock price crashes, consistent with results from the traditional logistic model.\n\n\nOriginality/value\nFirst, the ANN framework has been used in this study to forecast the stock price crashes and compared to the traditional logistic model in the world’s largest emerging market China. Second, the receiver operating characteristics curves and the area under the ROC curve have been used to evaluate the forecasting performance between the ANNs and the traditional approaches, in addition to some traditional performance evaluation methods.\n","PeriodicalId":46088,"journal":{"name":"Pacific Accounting Review","volume":" ","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2023-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pacific Accounting Review","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1108/par-08-2022-0121","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BUSINESS, FINANCE","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose
This paper aims to use artificial neural network (ANN) methods to predict stock price crashes in the Chinese equity market.
Design/methodology/approach
Three ANN models are developed and compared with the logistic regression model.
Findings
Results from this study conclude that the ANN approaches outperform the traditional logistic regression model, with fewer hidden layers in the ANN model having superior performance compared to the ANNs with multiple hidden layers. Results from the ANN approach also reveal that foreign institutional ownership, financial leverage, weekly average return and market-to-book ratio are the important variables when predicting stock price crashes, consistent with results from the traditional logistic model.
Originality/value
First, the ANN framework has been used in this study to forecast the stock price crashes and compared to the traditional logistic model in the world’s largest emerging market China. Second, the receiver operating characteristics curves and the area under the ROC curve have been used to evaluate the forecasting performance between the ANNs and the traditional approaches, in addition to some traditional performance evaluation methods.
期刊介绍:
Pacific Accounting Review is a quarterly journal publishing original research papers and book reviews. The journal is supported by all New Zealand Universities and has the backing of academics from many universities in the Pacific region. The journal publishes papers from both empirical and theoretical forms of research into current developments in accounting and finance and provides insight into how present practice is shaped and formed. Specific areas include but are not limited to: - Emerging Markets and Economies - Political/Social contexts - Financial Reporting - Auditing and Governance - Management Accounting.