An Intelligent CRM System for Identifying High-Risk Customers: An Ensemble Data Mining Approach

Lai, Kin Keung; Yu, Lean; Wang, Shouyang; Huang, Wei

doi:10.1007/978-3-540-72586-2_70

Cited by 3 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ngai strategy [1] asserts for example that concerning loyalty programs, 83.3% used classification models to assist in decision-making. Furthermore, these problems often come down to the binary classification for which the most used methods are: SVM [27,28], DT [29][30][31], ANN [32,33], RF [30,31,34,35], etc. Among these works, only one [36] has addressed the problem of modeling bank churn in the form of clustering using the k-means algorithm, which has been outperformed by the KHM algorithm.…”

Section: Related Workmentioning

confidence: 99%

Towards Explainable Machine Learning for Bank Churn Prediction Using Data Balancing and Ensemble-Based Methods

et al. 2022

View full text Add to dashboard Cite

The diversity of data collected on both social networks and digital interfaces is extremely increased, raising the problem of heterogeneous variables that are not often favourable to classification algorithms. Despite the significant improvement in machine learning (ML) and predictive analysis efficiency for classification in customer relationship management systems (CRM), their performance remains very limited by heterogeneous data processing, class imbalance, and feature scales. This impact turned out to be more important for simple ML methods which in addition often suffer from over-fitting. This paper proposes a succinct and detailed ML model building process including cross-validation of the combination of SMOTE to balance data and ensemble methods for modelling. From the conducted experiments, the random forest (RF) model yielded the best performance of 0.86 in terms of accuracy and f1-scoreusing balanced data. It confirms the literature summary about this topic which shows that RF was among the most effective algorithms for customer predictive classification issues. The constructed and optimized models were interpreted by Shapley values and feature importance analysis which shows that the “age” feature was the most significant while “HasCrCard” was the less one. This process has proven effective in bridging previously reported research gaps and the resulting model should be used for supporting bank customer loyalty decision-making.

show abstract