Accuracy Measure of Customer Churn Prediction in Telecom Industry using Adaboost over Decision Tree Algorithm
DOI:
https://doi.org/10.47750/pnr.2022.13.S04.179Keywords:
Customer Churn, Novel Adaboost Algorithm, Decision Tree Algorithm, Machine Learning, Telecom Industry, Data AnalyticsAbstract
Aim: To enhance and predict the accuracy rate of customer churning in the telecommunication industry using Adaboost over Decision Tree algorithm.
Materials and methods: Adaboost algorithm and Decision Tree algorithm with sample size (N=10) is executed with multiple training and testing splits for predicting the accuracy for customer churn prediction with 75% as g power value and threshold value as 0.000 and 95% as confidence interval . The performance of these algorithms are calculated based on the rate of accuracy using customer churn dataset.
Results and Discussion: The accuracy of predicting customer churn using Adaboost algorithm(90%) and Decision Tree algorithm (73%) is obtained. There was a analytical difference between the Novel Adaboost and Decision Tree algorithm is (p=0.000).
Conclusion: Prediction of customer churn using Novel Adaboost algorithm appears to be ((p<0.005) considerably greater than the Decision Tree algorithm with more accuracy percentage.
