Financial Performance Evaluation of Companies Using Decision Trees Algorithm and Multi-Criteria Decision-Making Techniques with an Emphasis on Investor’s Risk-Taking Behavior

سال انتشار: 1400
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 565

فایل این مقاله در 12 صفحه با فرمت PDF قابل دریافت می باشد

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

JR_AMFA-6-3_009

تاریخ نمایه سازی: 20 تیر 1400

چکیده مقاله:

Evaluating the performance of companies using their financial ratios is a challenging task that is expected to become more straightforward by reducing the dimensionality of the data. The purpose of this study is to evaluate the performance of companies using a hybrid model for investment-related decision making through which the mean value of various financial ratios are calculated based on the investor's risk-taking behavior so that the number of all criteria is reduced to one single value for each alternative. To do so, a sample of ۱۷۲ companies listed in Tehran Stock Ex-change was selected from ۲۰۰۸ to -۲۰۱۸. Firstly, the financial ratios were prioritized using decision trees regression analysis (type CART) and TOPSIS Technique. The results showed that Gross Profit Margin and Debt to Equity Ratio are the most and the least important factors, respectively. Then, using OWA (Ordered Weighted Averaging Aggregation) operator, the role of investor’s risk-taking behavior was investigated, and the results showed that investor’s risk-taking behavior changes the outcome of the decision-making process significantly.

نویسندگان

Zinat Ansari

Department of accounting, Yasooj Branch, Islamic Azad University, Yasooj, Iran

Rezvan Hejazi

Scientific Member of Financial & AMP; Economic Faculty, Khatam University, Tehran, Iran

Yaghoob Zeraat kish

Science and Research Branch, Islamic Azad university , Tehran, Iran

Zabihallah Khani Masoum Abadi

Department of Accounting, Fasa Branch, Islamic Azad University, Fasa, 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 :