Design of Long Short Term Memory Based Deep Learning Model for Customer Churn Prediction in Business Intelligence

International Journal of Advances in Applied Computational Intelligence IJAACI 2833-5600 10.54216/IJAACI https://www.americaspg.com/journals/show/2975 2022 2022 Design of Long Short Term Memory Based Deep Learning Model for Customer Churn Prediction in Business Intelligence University Of Applied Science, Faculty of Literature and Science, Manama, Bahrain Zahraa Zahraa University of Debrecen, Department of Mathematical and Computational Science, Debrecen, Hungary Dasha Stablichenkova Innovations in business intelligence are crucial in the digital era to staying popular and competitive across the increasing business trends. Businesses have started scrutinizing the next level of data analytics and business intelligence solutions. Customer Churn Prediction (CCP), on the other hand, a crucial for making business decisions, which correctly recognizes the churn customers and acts appropriately for customer retention. Customer churn is an unavoidable consequence when the user is not satisfied with the company’s service for a longer period. Service unsubscription by the user does not emerge unexpectedly; instead, it comes from the customer as a vigorous act owing to its accumulation of long-term disappointment. Thus, there is a need for the service provider to find and address their challenges related to customer satisfaction and service for retaining irate customers. The possibilities to predict customer churn have dramatically increased with the advances in artificial intelligence (AI) and machine learning (ML) algorithms. Therefore, this study introduces an Optimal Long Short Term Memory Based Customer Churn Prediction for Business Intelligence (OLSTM-CCPBI) method. The proposed OLSTM-CCPBI method incorporates many innovative components, such as Min-Max scaling for normalization, LSTM networks for temporal sequence modelling, and Adam optimization for hyperparameter tuning. The OLSTM-CCPBI method effectively captures temporal dependency in sequential customer data by leveraging the dynamic nature of the LSTM network, which enables correct prediction of churn events. Through detailed investigations on real-time customer churn datasets, OLSTM-CCPBI achieves better predictive capabilities than classical approaches, showcasing its promising solution to aid businesses in preemptively addressing customer attrition and considerably enhancing churn prediction accuracy. 2024 2024 56 64 10.54216/IJAACI.050105 https://www.americaspg.com/articleinfo/31/show/2975