Car insurance segmentation prediction based on the most influential features using random forest and stacking ensemble learning

In addition to financial transaction services, the Bank also provides insurance services by conducting regular campaigns to attract new customers such as car insurance based on market segmentation, which is one of the main aspects of marketing used in financial services based on demographic data. One way to analyze the market is to predict the likely target market based on the campaign's target demographic data. Therefore, this study aims to find the best classification method for predicting campaign targets using historical data from 4000 customers of a bank in the United States. The market segmentation analysis process uses the best feature selection and ensemble learning. The best feature selection is selected using important features for Random Forest. The ensemble learning used is a stacking model consisting of the basic model of Logistic Regression, Support Vector Classifier, Gradient Boosting, Extra Tree, Bagging, Adaboost, Gaussian Naive Bayes, MLP, XBoost, LGBM, KNeighbors, Decision Tree, and Random Forest. The accuracy results of the stacking model can exceed the accuracy of the basic model with an accuracy rate of 78.80%