Due to the increasingly significant competition inside and outside the aviation industry, airlines choose to conduct personalized sales to passengers for the purpose of increasing economic efficiency. In this paper, we select airlines customer information data during the period from 2012 to 2014, segment the value of air customers based on the LRFMC model and K-means algorithm. Then establish an airline customer churn prediction model, define churn customers, select characteristics, train SVM, Adaboost, RandomForest and Xgboost models, and then identify churn customers. Finally, the four models are compared and the optimal model is obtained. This article aims to classify airline customers so that airlines can adopt different marketing strategies for customers of different values to maximize profits. Improve the problem of customer churn, enable airlines to maintain their own markets, and bring high profits to airlines.
Airline Customer Value Analysis and Customer Churn Prediction Based on LRFMC Model and K-means Algorithm
2021-11-01
1314573 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Customer Churn Prediction using Machine Learning
IEEE | 2022
|Airline Member Customer Value Analysis: Data Visualization
VDE-Verlag | 2022
|