How to improve the success of bank telemarketing? Prediction and interpretability analysis based on machine learning

Modeling the Telemarketing Process Using Genetic Algorithms and Extreme Boosting: Feature Selection and Cost-Sensitive Analytical Approach

“…However, due to the imbalance distribution of the data and other characteristics, non of the related works was able to provide solutions that handle all the challenges faced in modeling this business issue [5], [7], [19]. Interestingly, most of the researchers agree that not all the dataset features have the same importance in understanding the intentions of the clients [4], [5], [7], [9], [10], [20]. Table 1 describes, in brief, some of the related works and the best-attained prediction performance in terms of Geometric Mean (GMean) and Type I Error.…”

“…Table 1 describes, in brief, some of the related works and the best-attained prediction performance in terms of Geometric Mean (GMean) and Type I Error. Some of the works listed in Table 1 reported the modeling performance of different approaches and Machine Learning (ML) algorithms [4], [6], [21] and some attempted to understand the significance of the specific dataset features in predicting the willingness of the client to accept an offer [5], [9], [10].…”

“…Proper handling of imbalanced data allows for better generalization of the prediction model to handle real-world scenarios without exhibiting any bias towards any of the target classes. Xie et al [4] proposed normalization to select features most effectively influencing a client's response to a telemarketing offer made by a bank. Further, they utilized "SMOTE", oversampling, to extend the minority class to overcome issues related to data imbalances.…”

“…BA of the banks' telemarketing process is challenging [4]- [6] due to the nature of the available data and the perceptional factors of the clients. Typically, historical data about the clients are imbalanced (i.e., the ratio between clients accepting an offer and those not interested is relatively very low), missing data usually is a concern, clients' intentions VOLUME 11, 2023 and attitudes may be affected by external factors (e.g., market dynamics, economic stability, etc), and the decision-makers are interested in understanding the factors affecting the intentions of the clients [5], [7].…”

“…In practice, researchers aim at leveraging the marketing process success rate either by implementing highly demanding and complex algorithms [5], [6], [8] (e.g., Deep Learning and Artificial Neural Networks) or employing approaches in which the original data are manipulated [4], [9]- [12] (e.g., resampling). Complex algorithms may generate competitive models but hinder the interpretation of the outcomes by decision-makers, and data manipulation may impose computational overhead or a distorted real-world representation of the problem.…”