USING BIG DATA AND AI TO PREDICT CONSUMER BEHAVIOUR IN E-COMMERCE

This study explores the integration of big data and advanced analytical techniques in predicting consumer behavior within e-commerce. The increasing role of data-driven decision-making in business operations has necessitated the adoption of more precise and adaptive analytical models to enhance marketing strategies, improve customer interaction, and optimize resource allocation. It has been determined that the implementation of intelligent data processing tools allows the identification of current consumer trends and the anticipation of behavioral shifts, providing businesses with a strategic advantage in a highly competitive digital marketplace. This research aims to assess the effectiveness of big data and artificial intelligence in forecasting consumer behavior, examine key approaches to their integration into business processes, and evaluate their practical applicability. The study employs comparative analysis, case study evaluation, and an assessment of the efficiency of implemented solutions based on real-world applications in e-commerce. The findings indicate that using artificial intelligence for consumer behavior analysis enhances forecasting accuracy, facilitates dynamic marketing adjustments, and strengthens customer engagement through personalized interactions. The automation of analytical processes enables businesses to respond more effectively to market fluctuations and consumer demands. However, challenges such as data reliability, privacy concerns, and algorithmic constraints remain critical issues that must be addressed to ensure ethical and transparent applications of these technologies. Several recommendations have been proposed to improve the precision and effectiveness of consumer behavior analysis. Emphasis is placed on refining adaptive predictive models, enhancing algorithm transparency, and implementing robust data protection measures. It has been established that improving data preprocessing techniques and optimizing analytical frameworks contribute to more accurate forecasting and better-informed decision-making in marketing strategies. The practical significance of this study lies in developing evidence-based recommendations for implementing artificial intelligence and big data analytics in e-commerce. These findings support businesses in achieving more accurate consumer insights, increasing the efficiency of marketing investments, and fostering sustainable customer relationships. Future research should focus on refining hybrid predictive models, examining the long-term impact of personalized recommendations on consumer decision-making, and developing regulatory guidelines for the responsible use of artificial intelligence in marketing analytics.