Customer churn prediction for web browsers
نویسندگان
چکیده
In the competitive web browser market, identifying potential churners is critical to decreasing loss of existing customers. Churn prediction based on customer behaviors plays a vital role in retention strategies. However, traditional churn algorithms such as Tree-based models cannot exploit temporal characteristics customers behaviors, while sequence explicitly extract information between multiple behaviors. To meet this challenge, we propose novel model named Multivariate Behavior Sequence Transformer (MBST) with two complementary attention mechanisms explore and behavioral separately. Furthermore, classifier attached for instead using multilayer perceptron. Extensive experiments real-world Tencent QQ dataset over 600,000 samples demonstrate that proposed MBST achieves F-score 82.72% Area Under Curve (AUC) 93.75%, which significantly outperforms state-of-the-art methods terms prediction.
منابع مشابه
ADTreesLogit model for customer churn prediction
In this paper, we propose ADTreesLogit, a model that integrates the advantage of ADTrees model and the logistic regression model, to improve the predictive accuracy and interpretability of existing churn prediction models. We show that the overall predictive accuracy of ADTreesLogit model compares favorably with that of TreeNet®, a model which won the Gold Prize in the 2003 mobile customer chur...
متن کاملData Mining Techniques in Customer Churn Prediction
Customer churn prediction is one of the most important problems in customer relationship management (CRM). Its aim is to retain valuable customers to maximize the profit of a company. To predict whether a customer will be a churner or non-churner, there are a number of data mining techniques applied for churn prediction, such as artificial neural networks, decision trees, and support vector mac...
متن کاملHandling class imbalance in customer churn prediction
0957-4174/$ see front matter 2008 Elsevier Ltd. A doi:10.1016/j.eswa.2008.05.027 * Corresponding author. Tel.: +32 9 264 89 80; fax: E-mail address: [email protected] (D. Va URL: http://www.crm.UGent.be (D. Van den Poel). Customer churn is often a rare event in service industries, but of great interest and great value. Until recently, however, class imbalance has not received much attent...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Expert Systems With Applications
سال: 2022
ISSN: ['1873-6793', '0957-4174']
DOI: https://doi.org/10.1016/j.eswa.2022.118177