An Effective Enterprise Earnings Management Detection Model for Capital Market Development

Abstract

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%.

Corporate social responsibility, CEO characteristics, and earnings management: Evidence from China

“…However, new technological techniques in the auditing field are gaining ground. Specifically, machine learning models are more likely to identify high‐risk firms at early stages; these are needed in future studies to obtain an additional measurement (for example, Chen & Shen, 2020; Jaspersen et al, 2021).…”

An investigation and analysis of working environment pollution in a lighter manufacturer

“…Establish the supervision and management system for the distribution of personal protective articles, especially to urge ultrasonic welding workers to wear noise proof earplugs or earmuffs correctly (SNR is 17-34 dB), urge the workers in injection molding workshop to wear dust masks of kn95 or above; and try to reduce the actual contact time of noise [9] .…”