Generative AI for Automating Consumer Behaviour Prediction in Marketing Strategies

Author

Mrs. Gorisetty Nirosha, Pothula Rama Sri

Abstract

 Consumer behaviour plays an important role in developing effective marketing strategies. Understanding customer preferences, purchasing patterns, product interests and feedback helps businesses make better marketing decisions. Traditional marketing approaches often depend on manual analysis and basic statistical techniques, which may not effectively handle large volumes of customer data. Recent developments in Artificial Intelligence (AI), Machine Learning (ML) and Generative AI provide opportunities to automate consumer behaviour analysis and support personalized marketing.

This paper proposes an integrated framework for consumer behaviour prediction using Machine Learning and Generative AI techniques. The proposed framework combines purchase behaviour prediction, customer segmentation, sentiment analysis and automated marketing insight generation. XGBoost is considered for predicting purchase behaviour, while K-Means and Hierarchical Clustering are considered for customer segmentation. Sentiment analysis is used to understand customer opinions from reviews and feedback. Generative AI is then used to convert the analytical outputs into meaningful customer insights and personalized marketing suggestions. The proposed approach aims to connect predictive analytics with automated marketing decision support. The framework is discussed in terms of its architecture, methodology, potential applications, expected outcomes and limitations. It provides a foundation for developing more data-driven and personalized marketing strategies.

Keywords

Generative AI, Consumer Behaviour Prediction, Machine Learning, XGBoost, Customer Segmentation, Sentiment Analysis, Personalized Marketing, Predictive Analytics.

Full Text:

Download Paper PDF

References

[1] Najafabadi, A. J., Skryzhadlovska, A., & Valilai, O. F. (2024). Agile product development by prediction of consumers’ behaviour; using neurobehavioral and social media sentiment analysis approaches. Procedia Computer Science, 232, 1683-1693.

[2] Chen, X. (2025). Consumer Online Shopping Behavior Prediction Based on Machine Learning Algorithm. Procedia Computer Science, 262, 1395-1401.

[3] Lee, S., Pu, Z., Goetzinger, G., Preisach, C., Haft, M., Southall, A., & Vogel, A. (2025). U.S. Patent Application No. 13/239,922.

[4] GhorbanTanhaei, H., Boozary, P., Sheykhan, S., Rabiee, M., Rahmani, F., & Hosseini, I. (2024). Predictive analytics in customer behavior: Anticipating trends and preferences. Results in Control and Optimization, 17, 100462.

[5] Cai, B. (2024). Research on consumer behavior and prediction based on deep learning in the new energy vehicle market. Procedia Computer Science, 247, 351-357.

[6] Lajoie, P. L. (2025). Content marketing as a propaganda vehicle for a romantic-managerial conception of artificial intelligence. Critical Perspectives on Accounting, 102, 102810.

[7] Lafuente, S. G., Prados-Castillo, J. F., Guaita-Martínez, J. M., & Ribeiro-Soriano, D. (2026). Digital transformation, artificial intelligence, and sustainable marketing strategies in cooperatives. Sustainable Technology and Entrepreneurship, 100138.

[8] Dong, X., Feng, Z., Yu, X., Zhang, J., & Jia, H. (2024). Evolution prediction method for electric private car ownership considering the decision-making behavior of consumers. Energy Reports, 11, 498-509.

[9] Prakash, K. P., Kumar, Y. P., Reddy, C. P., Pradeep, D. J., Flah, A., Alzaed, A. N., ... & Ghoneim, S. S. (2025). A comprehensive analytical exploration and customer behavior analysis of smart home energy consumption data with a practical case study. Energy Reports, 8, 9081-9093.

[10] Wuyart, A., & Millot, J. M. (2026). Generative AI for CSF multi-omics: Learning strategies for small-cohort classification. Neuroscience Informatics, 100278.

Share your valuable work from Social Media Buttons