Proposed Integrated Customer Churn Predication Model using Several Statistical Feature Scaling and Machine Learning Algorithms

Data science is crucial for analytics and prediction in the telecommunication industry.Customer churn prediction is becoming progressively important. While machine learning methodsare regularly utilized for predicting churn, their performance can be improved due to thecomplexity of consumer data structures. Managers lose trust when findings are difficult tointerpret .This study utilizes data preprocessing techniques. The various elements of benchmarkeddata collecting can impact interpretability since imbalanced and feature scaling issues. Therefore,this study develops customer churn prediction model for those complexity issues. After trainingthe model, the operator analyzes the data to understand its performance. To maximizeinterpretability, consumers are clustered based on behavioral factors. Clustering is grouping datapoints with similar features to maximize similarity between members. Additionally, they share fewsimilarities with members of other groups. Using homogeneous group members improvesclassification algorithm prediction performance. Various algorithms, including logistic regression,support vector machine, random forest, Ada-boost, and multilayer perceptron, were tested beforeand after hyperparameter adjustment to achieve optimal prediction performance.