• Keerthi Chandana Gorla
• Shashi Krishna Ayachitula
• Sriram Ponnam
• Bhavani Kathram
• B.Raju

This study addresses the pressing need for effective customer churn prediction within the realm of business analytics, particularly focusing on leveraging Azure Databricks for enhanced predictive modeling. Through a systematic literature review (SLR), the research examines various methodologies and techniques for customer churn prediction, emphasizing the utilization of Azure Databricks advanced analytics capabilities. The study explores architectural mechanisms that support the development of accurate predictive models while considering factors such as data interoperability, scalability, and security. Additionally, the research proposes a high-level architecture tailored to Azure Databricks, integrating key components such as data preprocessing, feature engineering, and model deployment. Noteworthy is the emphasis on utilizing Azure Databricks' collaborative workspace and scalable computing resources to streamline the model development process. The study also highlights the importance of feature selection and model evaluation techniques in enhancing predictive accuracy. However, the research acknowledges the challenges associated with balancing model complexity and interpretability, as well as the evolving landscape of both data analytics and customer behavior. By providing insights into the architectural design and validation processes, this study contributes to the advancement of customer churn prediction using Azure Databricks, with the overarching goal of improving business decision-making and customer retention strategies in today's competitive market landscape.

Customer Churn Prediction , Azure Databricks , Business Analytics , Predictive Modeling , Advanced Analytics, Architectural Mechanisms , Data Interoperability , Scalability ,Security , Data Preprocessing , Feature Engineering , Model Deployment ,Collaborative Workspace ,Machine Learning Algorithms ,Deep Learning ,Model Evaluation Techniques ,Data Quality Model Interpretability ,Real-time Prediction ,Cloud Computing Platforms

"Customer Churn Prediction With Azure Databricks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.d678-d683, May-2024, Available :http://www.jetir.org/papers/JETIR2405377.pdf

"Customer Churn Prediction With Azure Databricks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppd678-d683, May-2024, Available at : http://www.jetir.org/papers/JETIR2405377.pdf