Fraud Risk Prediction in Financial Statements through Comparative Analysis of Genetic Algorithm, Grey Wolf Optimization, and Particle Swarm Optimization
محل انتشار: مجله مالی ایران، دوره: 8، شماره: 1
سال انتشار: 1403
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 32
فایل این مقاله در 33 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_IJFIFSA-8-1_005
تاریخ نمایه سازی: 29 اردیبهشت 1403
چکیده مقاله:
Financial statements are critical to users, as the increasing fraud cases have left behind irreversible impacts. Hence, this study aims to identify the appropriate financial ratios for fraud risk prediction in the financial statements of companies listed on the Tehran Stock Exchange within the ۲۰۱۴–۲۰۲۱ period. The study is based on data from ۱۸۰ companies listed on the Tehran Stock Exchange, encompassing a total of ۱۴۴۰ financial statements. To select the most appropriate ratios for fraud risk prediction, all financial ratios were tested by three metaheuristic algorithms, i.e., genetic algorithm, grey wolf optimization, and particle swarm optimization. Metaheuristic and data mining methods were employed for data analysis, and these analyses were conducted using MATLAB R۲۰۲۰a (MATLAB ۹.۸). According to the research results, the fitness function yielded ۰.۲۷۰۸ in particle swarm optimization (PSO). With an accuracy of ۷۲.۹۲% after ۱۹ iterations, PSO was more accurate and converged faster than the other algorithms. It also extracted ۱۱ financial ratios: total debts to total assets, working capital to total assets, stock to current asset, accounts receivables to sales, accounts receivables to total assets, gross income to total assets, net income to gross income, current assets to current debt, cash balance to current debt, retained earnings and loss to equity, and long-term debt to equity. The support vector machine (SVM) classifier was then employed for fraud risk detection at companies through the ratios extracted by the proposed algorithms. The accuracy and precision of financial ratios extracted by PSO and SVM were reported at ۸۰,۶۰% and ۷۱,۲۰%, respectively, which indicates the superiority of the proposed model to other models. Considering that the results obtained from the performance evaluation of financial ratios provided by PSO-SVM demonstrate the capability of this method in predicting the likelihood of fraud in financial statements, it can assist financial statement users. By incorporating these ratios about the performance of the target companies and comparing them with those of other companies, users can make more informed decisions in economic decision-making, investments, credit assessments, and more, ultimately minimizing potential losses and risks.
کلیدواژه ها:
Financial Ratios ، Metaheuristic Algorithm ، Particle Swarm Optimization ، and Support vector machine
نویسندگان
Zahra Nemati
Ph.D. Candidate, Department of Accounting, Zanjan Branch, Islamic Azad University, Zanjan, Iran.
Ali Mohammadi
Assistant Prof., Department of Accounting, Zanjan Branch, Islamic Azad University, Zanjan, Iran.
Ali Bayat
Assistant Prof., Department of Accounting, Zanjan Branch, Islamic Azad University, Zanjan, Iran.
Abbas Mirzaei
Assistant Prof., Department of Computer Engineering, Ardabil Branch, Islamic Azad University, Ardabil, Iran.
مراجع و منابع این مقاله:
لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :
