Clasificación de clientes de empresas aseguradoras según el uso de servicios de salud, utilizando KDD y Aprendizaje Automático

Abstract

Abstract: Artificial Intelligence at the service of business sectors such as the insurance sector, allows managers to adopt customer service strategies in order to improve customer satisfaction, ensuring their loyalty. This project is based on the identification of the problems of the insurance sector, and its purpose is to build a customer classification model of insurance companies, based on the use of health services, through the application of supervised Machine Learning models such as Logistic Regression, XGBClassifier, Random Forest Classifier, Naive Bayes; unsupervised such as Principal Component Analysis (PCA) and K-means; and, Deep Learning models such as Convolutional Neural Networks. Its application is based on performing several experiments to achieve the best classification model by evaluating metrics such as Accuracy, Precision, F1-score, Roc-auc. Additionally, a prototype is built that allows the visualization and obtaining of classification results; information that, together with the discovery of patterns in the data, can be used for decision making.