• Pritam Ahire
• Atharva Wankar
• Yashashree Mahajan
• Vaibhav Zope

Customer attrition, also known as churn, is a big problem for businesses across all sectors, as retaining existing customers is more cost-effective than finding new ones. Because there are a lot fewer churners than non-churners, traditional machine learning (ML) models for churn prediction frequently have class imbalance. Biassed models that are unable to anticipate attrition properly are the result of imbalance. A new strategy for enhancing attrition prediction is proposed by fusing machine learning techniques with Generative Adversarial Networks (GANs). GANs generate synthetic churn data, improving dataset balance and increasing model accuracy. We evaluate the impact of GAN-generated data on ML models like Random Forest and Artificial Neural Networks (ANN). Results demonstrate that GAN-augmented datasets significantly improve model recall and F1-score, enabling better identification of at-risk customers.

Customer Attrition, Churn Prediction, Generative Adversarial Networks (GANs), Machine Learning, Random Forest, Artificial Neural Networks (ANN), Data Augmentation, Feature Selection, Imbalanced Data, Customer Retention, Predictive Analytics, Synthetic Data Generation.

"Customer Attrition Prediction Using Generative Adversarial Networks (GANs) and Machine Learning (ML)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.c51-c59, March-2025, Available :http://www.jetir.org/papers/JETIR2503207.pdf

"Customer Attrition Prediction Using Generative Adversarial Networks (GANs) and Machine Learning (ML)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppc51-c59, March-2025, Available at : http://www.jetir.org/papers/JETIR2503207.pdf