With the rapid advancement of big data analytics and deep learning technologies, their applications have expanded beyond traditional domains into marketing and customer relationship management. One of the critical challenges in marketing is customer churn management, which focuses on identifying and retaining customers who are likely to discontinue their engagement with a brand or service. This project aims to prevent customer churn and enhance purchase conversion rates by issuing personalized discount coupons to at-risk customers in real time, based on big data insights. The proposed system segments customers using two-dimensional cluster analysis, allowing precise identification of churn-prone groups. By integrating deep learning models, the system predicts the most suitable coupons for each customer segment, thereby improving retention strategies and engagement outcomes. The churn rate estimation process enables businesses to take proactive measures before customer loss occurs. Ultimately, this data-driven approach enhances conversion rates, drives sales growth, and contributes to more efficient and intelligent marketing decision-making within competitive business environments.

In this project we have detected, and segmented the customer data using Python, ML models. First ,we have to upload a dataset of customers data which is taken from shopping malls. The system is detected into two-dimensional analysis that are present in ML. After that the next phase which is recommending the coupons to customer which are paytm voucher, movie, restaurant to customer by using the scikit learn framework. We are suggesting the coupon to the customer based on the performance metrics like accuracy.

1.P. Naval and N. Pandey, ‘‘What makes a consumer redeem digital coupons?Behavioral insights from grounded theory approach,’’ J. Promotion Manage., vol. 28, no. 3, pp. 205–238, 2021. 2.M. Sarkar and A. D. Bruyn, ‘‘LSTM response models for direct marketing analytics: Replacing feature engineering with deep learning,’’ J. Interact.Marketing, vol. 53, pp. 80–95, Feb. 2021. 3.Y. Chen, M. Zhou, Z. Zheng, and D. Chen, ‘‘Time-aware smart object recommendation in social Internet of Things,’’ IEEE Internet Things J., vol. 7, no. 3, pp. 2014–2027, Mar. 2020. 4.G. Chandrasekaran and D. J. Hemanth, ‘‘An intelligent framework for online product recommendation using collaborative filtering,’’ in Proc. Int. Conf. Sustain. Expert Syst. (ICSES). Cham, Switzerland: Springer, 2021,p. 249. 5.G. Nie, ‘‘Finding the hidden pattern of credit card holder’s churn: A case of China,’’ in Proc. Int. Conf. Comput. Sci. Cham, Switzerland: Springer, 2009, pp. 561–569.. 6.R. M. Gubela, S. Lessmann, and S. Jaroszewicz, ‘‘Response transformation and profit decomposition for revenue uplift modeling,’’ Eur. J. Oper. Res., vol. 283, no. 2, pp. 647–661, Jun. 2020. 7.S.-J. Lim, Z. Lee, L.-N. Kwon, and H.-W. Chun, ‘‘Medical health records based mild cognitive impairment (MCI) prediction for effective dementia care,’’ Int. J. Environ. Res. Public Health, vol. 18, no. 17, p. 9223, Sep. 2021. 8.Y. Yoo, T.-S. Heo, Y. Park, and K. Kim, ‘‘A novel hybrid methodology of measuring sentence similarity,’’ Symmetry, vol. 13, no. 8, p. 1442, Aug. 2021. D. Koehn, S. Lessmann, and M. Schaal, ‘‘Predicting online shopping behaviour from clickstream data using deep learning,’’ Expert Syst. Appl., vol. 150, Jul. 2020, Art. no. 113342.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close