The information within financial news headlines plays a crucial role in predicting stock market movements and providing valuable insights for investors. This study focuses on assessing the impact of financial news headlines sourced from Thomson Reuters on the stock returns of Apple (AAPL) from December 30th, 2011, to May 31st, 2019, with the goal of developing a profitable trading strategy. In the data preparation phase, we meticulously clean, tokenize, and extract features from the headlines. By employing sentiment analysis through the Financial Bidirectional Encoder Representations from Transformers (BERT) model, we establish a link between the sentiment of Apple’s news and its corresponding stock prices. Subsequently, we utilize various statistical machine learning (SML) models, such as Decision Trees (Breiman et al., Classification and regression trees, 1984), Random Forests (Breiman in Machine learning. Springer, pp 5–32, 2001), and Neural Networks (Lawrence in Introduction to neural networks. California Scientific Software, 1993), with stratified cross-validation for performance evaluation and hyperparameter tuning. Additionally, the study explores trading strategies that utilize European call and put options, leveraging predictions generated by the SML models. By exploring the relationship between financial news headlines and stock market fluctuations, our research provides valuable insights. Investors can optimize their trading strategies and make informed decisions by understanding this intricate relationship.