• Yunus Ahmed
• Tushar Kumar Pandey
• Dr. V. Deeban Chakravarthy

This study delves into the multifaceted landscape created by China's rapid economic growth, which has not only provided consumers with an extensive array of spending options but has also posed a substantial challenge for businesses in the form of customer attrition. The proposed methodology for predicting customer attrition represents a systematic and data-driven approach designed to address the challenge of customer churn. This comprehensive methodology encompasses various stages and components, beginning with thorough data collection that spans customer behavior, demographics, and historical patterns. Subsequent data preprocessing ensures data quality, including cleaning and handling missing values. Feature selection identifies key attributes influencing customer attrition, while advanced analytics and machine learning models leverage these features for predictive purposes. Incorporating LightGBM as the core model, the proposed methodology focuses on interpretability and performance. It emphasizes understanding the drivers of churn predictions, enabling tailored retention strategies. The methodology also integrates customer satisfaction evaluation, providing a holistic view of customer attrition. Continuous monitoring, feedback loops, and security measures ensure the model remains effective and compliant with privacy regulations. The analysis of leasing rate ranges reveals that leasing rates between $50 and $100 have a substantial impact on customer turnover (30% churn rate). Rates between $100 and $150 also significantly influence churn (20%), highlighting the need for rate adjustments for improved retention. Rates above $150 show progressively less impact on churn, with rates above $200 having negligible effects. Ultimately, the goal of this methodology is to contribute to informed decision-making, improved customer satisfaction, and business growth and resilience.

"A Data Mining-Backed Early Warning System Harnessing Mobile Communication Technology", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 9, page no.d445-d451, September-2023, Available :http://www.jetir.org/papers/JETIR2309344.pdf

"A Data Mining-Backed Early Warning System Harnessing Mobile Communication Technology", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 9, page no. ppd445-d451, September-2023, Available at : http://www.jetir.org/papers/JETIR2309344.pdf