A High-Performance Customer Churn Prediction System Based on Self-Attention

Wu, H. R.

doi:10.2139/ssrn.4145486

Cited by 5 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to make the contrast in customer churn more obvious, we use the pie chart in Figure 2 to represent the proportion of the two samples [6]. From the pie chart, we can draw a conclusion that the number of retained users exceeds the number of lost users by a factor of three.…”

Section: Data Preparationmentioning

confidence: 99%

See 1 more Smart Citation

Customer churn prediction based on a novelty hybrid random forest algorithm

Zhang

2023

Third International Conference on Computer Vision and Data Mining (ICCVDM 2022)

View full text Add to dashboard Cite

With the rapid growth of the economy and consumption, the phenomenon of customer churn becomes more and more rampant. Therefore, predicting whether customers' churn behavior has become a necessary means for enterprises, society, and even the whole country to develop an economic system and create an economic system to ensure that cash flow is not blocked. In fact, the data related to customer prediction have features of huge magnitude and diverse dimensions. Therefore, organizations often need to invest high costs to complete a series of feature projects to capture and analyze feature variables. However, due to the large and complex data, the accuracy of feature engineering is difficult to be guaranteed. Inspired by this phenomenon, this paper proposes a high-quality and good-performance RF-MLP algorithm. Through the training of random forest, the data is filtered and screened and then combined with an artificial neural network to transform the screening results, capturing high-level and nonlinear feature variables and finally achieving stronger model fitting. In this study, the feasibility of the algorithm model is verified by a real and effective data set of customer churn. According to the experimental results, the AUC score of RF-MLP in the test set is 84.9%, which is 9.1% and 21.7% higher than that of the RF and MLP algorithm alone.

show abstract

Section: Data Preparationmentioning

confidence: 99%

“…Currently, researchers in customer churn prediction generally adopt three methods: Individual machine learning, Ensemble machine learning, and Deep Learning [6]. Among them, there are four main individual machine learning models: Logistic Regression, Decision Tree [7], Support Vector Machine (SVM) [8], and Multi-Layer Perceptron (MLP) [9].…”

Section: Introductionmentioning

confidence: 99%