Revisiting AI and Machine Learning Techniques in Finance and Economics: A Regression-Based Perspective

Artificial Intelligence (AI) and Machine Learning (ML) techniques are transforming modern finance and economics by improving predictive accuracy, decision-making processes, and risk assessment models. This study revisits the role of AI and ML approaches in analyzing financial and macroeconomic dynamics, emphasizing their application in forecasting economic growth, financial stability, and investment performance. The research employs a regression-based framework integrating traditional econometric models with machine learning algorithms to examine the relationship between economic indicators and financial outcomes.The proposed empirical model is specified as:GDP_t = \beta_0 + \beta_1 INF_t + \beta_2 GC_t + \beta_3 CO2_t + \beta_4 AI_t + \varepsilon_t
where GDP_t represents economic growth, INF_t inflation, GC_t green credits, CO2_t carbon emissions, and AI_t the artificial intelligence and machine learning index used to capture technological integration in financial systems. The study combines Ordinary Least Squares (OLS), Random Forest Regression, and Neural Network models to compare forecasting efficiency and explanatory power.Using panel data from Western Balkan countries for the period 2010–2025, the findings are expected to demonstrate that AI-enhanced financial systems contribute positively to economic resilience, sustainable investments, and risk mitigation. Furthermore, machine learning techniques outperform traditional regression methods in identifying nonlinear relationships and hidden financial patterns.The study contributes to the growing literature on digital finance and sustainable economic development by providing evidence on how AI-driven analytical models can support policymakers, financial institutions, and investors in improving strategic decision-making under economic uncertainty.