Akademik Veri Yönetim Sistemi
International Econometric Review, cilt.17, sa.1, ss.44-58, 2025 (TRDizin)
The objective of this study is to predict the monthly closing prices of the BIST Bank Index(XBANK) utilising macroeconomic and financial indicators. The explanatory variablesencompass the real exchange rate, inflation, the consumer confidence index, the policy rateof the Central Bank of the Republic of Türkiye (CBRT), the growth rate of M2 moneysupply, CBRT reserves, deposits, the industrial production index, the Türkiye CDS spread,and the VIX fear index. In the initial evaluation, three machine learning models –GradientBoosting, XGBoost, and RandomForest Regressor – with the highest predictivepower were identified using the LazyRegressor method, and hyperparameter optimizationwas performed on these models. The performance of the models was evaluated using theR² and RMSE criteria. The most successful result was obtained with the GradientBoostingmodel, which had an R² score of 0.99. Pursuant to feature importance analysis, it wasdetermined that inflation (37%), policy interest rate (29%), and Central Bank of theRepublic of Türkiye (CBRT) reserves (13%) were the variables exerting the most influenceon the movements of the banking index. The findings of this study suggest that monetarypolicy and macroeconomic stability exert a significant influence on the stock performanceof the Turkish banking sector.