Prediction of stock returns with artificial neural networks and regression methods: An application on BİST-30

With the rapid development of technology in the world in recent years, many innovations have emerged in the field of artificial intelligence. With these innovations, one of the most used areas of artificial intelligence has been finance. Predicting the future is often needed in finance. There are many statistical methods used to make predictions. Among these methods, Artificial Neural Networks (ANN) is one of the most preferred methods In this thesis, 3 different portfolios were created by taking the closing prices of the 12 stocks included in BIST-30 for the three-month periods of the years 2019 and 2020. The portfolios created were first examined by panel regression analysis, considering some financial criteria. Afterwards, the closing prices of the stocks were estimated by using Artificial Neural Networks and Regression Analysis. The results were compared and it was seen that the results obtained with the Artificial Neural Networks method were more successful than the performance criteria.