The purpose of this study is to establish rigorous and reliable going concern doubt (GCD) prediction models. This study first uses the least absolute shrinkage and selection operator (LASSO) to select variables and then applies data mining techniques to establish prediction models, such as neural network (NN), classification and regression tree (CART), and support vector machine (SVM). The samples of this study include 48 GCD listed companies and 124 NGCD (non-GCD) listed companies from 2002 to 2013 in the TEJ database. We conduct fivefold cross validation in order to identify the prediction accuracy. According to the empirical results, the prediction accuracy of the LASSO–NN model is 88.96 % (Type I error rate is 12.22 %; Type II error rate is 7.50 %), the prediction accuracy of the LASSO–CART model is 88.75 % (Type I error rate is 13.61 %; Type II error rate is 14.17 %), and the prediction accuracy of the LASSO–SVM model is 89.79 % (Type I error rate is 10.00 %; Type II error rate is 15.83 %).

The purpose of this study is to establish an effective financial distress prediction model by applying hybrid machine learning techniques. The sample set is 262 financially distressed companies and 786 non-financially distressed companies, listed on the Taiwan Stock Exchange between 2012 and 2018. This study deploys multiple machine learning techniques. The first step is to screen out important variables with stepwise regression (SR) and the least absolute shrinkage and selection operator (LASSO), followed by the construction of prediction models, as based on classification and regression trees (CART) and random forests (RF). Both financial variables and non-financial variables are incorporated. This study finds that the financial distress prediction model built with CART and variables screened by LASSO has the highest accuracy of 89.74%.

The going-concern opinions of certified public accountants (CPAs) and auditors are very critical, and due to misjudgments, the failure to discover the possibility of bankruptcy can cause great losses to financial statement users and corporate stakeholders. Traditional statistical models have disadvantages in giving going-concern opinions and are likely to cause misjudgments, which can have significant adverse effects on the sustainable survival and development of enterprises and investors’ judgments. In order to embrace the era of big data, artificial intelligence (AI) and machine learning technologies have been used in recent studies to judge going concern doubts and reduce judgment errors. The Big Four accounting firms (Deloitte, KPMG, PwC, and EY) are paying greater attention to auditing via big data and artificial intelligence (AI). Thus, this study integrates AI and machine learning technologies: in the first stage, important variables are selected by two decision tree algorithms, classification and regression trees (CART), and a chi-squared automatic interaction detector (CHAID); in the second stage, classification models are respectively constructed by extreme gradient boosting (XGB), artificial neural network (ANN), support vector machine (SVM), and C5.0 for comparison, and then, financial and non-financial variables are adopted to construct effective going-concern opinion decision models (which are more accurate in prediction). The subjects of this study are listed companies and OTC (over-the-counter) companies in Taiwan with and without going-concern doubts from 2000 to 2019. According to the empirical results, among the eight models constructed in this study, the prediction accuracy of the CHAID–C5.0 model is the highest (95.65%), followed by the CART–C5.0 model (92.77%).

The purpose of this study was to build a highly accurate corporate financial distress tracking and prediction model based on hybrid machine learning technology. The research data were from Taiwan Economic Journal, and the research subjects were enterprises with financial distress risk announced in September 2022. In consideration of enterprise features, this study excluded the finance and insurance industries. The research period was three years (2019, 2020, and 2021) before the distress announcement. This study matched enterprises with financial distress and enterprises without financial distress (normal enterprises) at a ratio of 1:1 for each year. The sample size for each year included 374 enterprises with financial distress and 374 enterprises without financial distress. This study applied several machine learning technologies. At first, important variables were screened by applying artificial neural networks (ANNs). Next, prediction models were built based on decision tree C5.0 and random forest (RF) and were compared. According to the empirical result, the ANN-RF model provided a higher accuracy.

This study focuses on accrual-based earnings management. The purpose of this study is to establish an innovative and high-accuracy model for detecting earnings management using hybrid machine learning methods integrating stepwise regression, elastic net, logistic regression (Logit regression), and decision tree C5.0. Samples of this study are the electronic companies listed on the Taiwan Stock Exchange, and data are derived from the Taiwan Economic Journal (TEJ) for a period of ten years from 2008 to 2017. Results show that the earnings management detection model, as established by elastic net and C5.0, provides the best classification performance, and its average accuracy reaches 97.32%.