نوع مقاله : مقاله پژوهشی فارسی
نویسندگان
1 گروه حسابداری، دانشکده مدیریت و حسابداری، دانشگاه ایلام، ایلام، ایران.
2 دانشجوی دکتری، گروه حسابداری، دانشگاه علامه طباطبایی، تهران، ایران
3 استادیار، گروه حسابداری، دانشگاه علامه طباطبایی، تهران، ایران
4 دکترای حسابداری، دانشگاه علامه طباطبایی، تهران، ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Objective : The present study seeks to analyze unstructured data from the annual report and combine it with quantitative financial information to predict financial distress through text mining techniques and machine learning algorithms.
Method: Using the fuzzy Delphi method, quantitative variables affecting financial distress were identified based on the opinion of experts and their quantitative information was extracted from financial statements and then , the report of 100 companies listed in the period 2013 - 2023 were collected and after converting the corresponding PDF files to the Word files , by using python programming language , data mining ( including preprocessing , feature extraction , feature selection , etc. ) was developed .
Findings: The prediction results indicate the high predictive power of SVM model with radial kernel compared to other models. So that its ability to predict financial distress based on three quantitative, qualitative and integrated methods is 85, 91 and 92% respectively.
Conclusion: The results of this research showed that instead of just paying attention to the numbers and the ratios derived from these numbers, the text mining technique can also be used for analysis and prediction, and by combining it with the results obtained from quantitative information, the financial distress of companies can be determined. Although the accuracy of predicting results from unstructured data compared to structured data with a predictability about 90% is less, but knowing and using the capacity of this type of information is very important.
کلیدواژهها [English]
)