This thesis explores the integration of machine learning techniques into financial statement analysis and forecasting within the context of the Nigerian Banking Industry. The primary objectives are to predict the financial health and profitability of companies, enhance data-driven investment decisions, reduce the risk of financial losses for investors, and advance the application of machine learning in finance by substituting traditional analysis methods. The study focuses on GTCO Plc, a prominent entity listed on the Nigerian Stock Exchange. Initially, traditional annual report analysis serves as a foundation for understanding the company's financial performance. Subsequently, a predictive model is developed using four machine learning algorithms: Random Forest, K-Nearest Neighbor, Logistics Regression, and Naïve Bayes.
