Combination of Extreme Learning Machine and Binary Bat Algorithm for Customer Churn Prediction

AbstractOne of the important assets in a company is customers. Customers determine the company's stability because they are source of income and determine the company's competitiveness. It shows the importance of predicting which customers have the potential to switch to another company. These predictions can be done using Machine Learning (ML). One of ML methods is the Extreme Learning Machine (ELM). The advantages of ELM compared to other methods are fast computing time, ease of use, and can reach a global optimum. However, ELM has weaknesses when solving problems with high-dimensional datasets, so feature selection is required. The Binary Bat Algorithm (BBA) is a swarm intelligence method that can be used to optimize ELM performance. The advantages of BBA compared to other are few parameters and much better in effectiveness or accuracy. This research was carried out with preprocessing data, training data and testing data. The research results showed that ELM-BBA is better than ELM and ELM-Binary Particle Swarm Optimization (BPSO) in evaluation metric values. However, ELM-BBA tended to be slower than ELM-BPSO. The best results on evaluation metrics achieved by ELM-BBA were 0.97, 0.97, 0.96, and 0.97 in accuracy, precision, recall, and F1 score, respectively.