Abstract:

The aim of the study is to estimate the risk of financial failure of enterprises by using machine learning, one of the artificial intelligence techniques. In this context, machine learning methods NaiveBayes, J48, RandomForest, LinearRegression, RandomTree were used with 43 financial ratios obtained from the financial statements of 14 companies in Borsa Istanbul Main Market and 14 companies in Borsa Istanbul Watchlist Market for the year 2022. With the data obtained using the financial statements of the companies, it is investigated which of the machine learning application models provides better classification accuracy. In addition, it was tested whether it is possible to predict the financial situation of a company in the close monitoring market in 2022 for the following year with machine learning. It was concluded that the highest classification accuracy rate was achieved by applying the RandomForest algorithm and 10-fold cross-validation technique together, while the NaiveBayes algorithm and 10-fold cross-validation technique achieved a very high rate of success in the prediction model for a single year.

Keywords: