Integration of Business Analytics and Big Data for predicting investor behavior in stock markets

Abstract

The article addresses the pressing issues of forecasting investor behavior under conditions of increasing information saturation of stock markets and the growing influence of behavioral and emotional factors. The purpose of this study is to provide theoretical and methodological justification for integrating Big Data and Business Intelligence (BI) tools into the system of investor behavior forecasting, thereby enhancing the accuracy, transparency, and comprehensiveness of assessments. Methods. The research employs system analysis methods to identify the limitations of traditional approaches, comparative analysis to highlight the advantages of modern technologies, and structural-logical modeling to develop the authors’ analytical frameworks. The study results include a critical review of traditional forecasting methods and their main limitations; systematization of modern tools (Big Data Analytics, BI, ML, NLP, Predictive Analytics) and demonstration of their advantages in the financial sphere; substantiation of BI platform integration with large-scale data and architectural solutions (Data Lake, Hadoop, Spark, MLOps). Two original frameworks are proposed – the integration form of personalized analytics and the ESG-oriented form of investor behavior forecasting, which combine forecasting methods with specific indicators and evaluation scales. Their application enables the consideration of both quantitative characteristics and investor behavioral patterns, as well as intangible factors of sustainable development, thereby making forecasting more systematic, adaptive, and practically relevant. It is demonstrated that the proposed approaches can enhance forecast accuracy, standardize results, and strengthen trust in financial analytics. Conclusions. The practical value of the study lies in the possibility of applying the developed forms by different user groups, including investors for building individual strategies, financial analysts for improving forecasting models, and regulators for enhancing the transparency and predictability of the stock market. The proposed results lay the groundwork for shaping a new paradigm of investor behavior forecasting that integrates technological innovations with the principles of sustainable development.