Value investing with machine learning: European market

Abstract

This dissertation explores the application of machine learning techniques for value investing in the European stock market. The study leverages various deep learning models, including CNN-LSTM, CNN, CNN-GRU, and CNN-RNN, to predict stock prices and identify high-yield investments. The research demonstrates that ASML has the highest predicted three-year average stock price return among one hundred companies, with CNN-LSTM achieving the most promising results. The study highlights the utility of deep learning in stock price forecasting and its potential to enhance investment strategies. The findings suggest that while deep learning models show promise, they also have limitations that need addressing. The dissertation concludes with recommendations for future research and practical investment strategies, emphasizing the importance of integrating machine learning insights with traditional financial analysis.