A grid search optimized extreme learning machine approach for customer churn prediction

Customers' behaviors such as tendencies, loyalty status, satisfaction criteria show an alteration day by due to the changing world. So, these behavior changes should be analyzed very well in every step of decision-making process. Customer churn analysis is determination customers who tend leave analyzing customer data with various methods before this situation occurs. This study aims develop Extreme Learning Machine based model for prediction problem and determine parameters that provide best performance. Grid search used hyperparameter tuning. Also modified accuracy calculation approach has been presented. The set obtained from UCI Repository used. Naive Bayes, k-Nearest Neighbor Support Vector are selected performance comparison model. With a value 93.1%, measure Machine. Due low number determined evaluation measures compete other models’ results, it can said highly effective interesting solution problem.