Open AccessBank Direct Marketing Analysis Based on Ensemble Learning
Author(s) -
Ruiting Hao,
Xiaoqian Xia,
Siyi Shen,
Xiaorong Yang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1627/1/012026
Subject(s) - direct marketing , boosting (machine learning) , ensemble learning , computer science , classifier (uml) , machine learning , the internet , artificial intelligence , database marketing , marketing , data mining , business , relationship marketing , marketing management , world wide web
In the era of Internet and big data, the bank has gradually realized that the traditional data analysis cannot meet the demands of the existing marketing. So the bank direct marketing based on machine learning emerges. However, there are few references which are completely based on ensemble learning. As different banks have different structures of customer data, the existing model cannot be employed directly. Therefore, this article collects the marketing data of a Portugal’s bank and compares the classification effects of six different models under three ensemble learning algorithms ---“Boosting”, “Bagging” and “Stacking”, respectively. Then we select the most appropriate model which has the best performance as the final classifier. Banks can use the classifier to judge whether a customer will order financial products and make direct marketing plans.