Improving Efficiency of Machine Learning Model for Bank Customer Data Using Genetic Algorithm Approach

Ram, Babu; Kumar, Dinesh; Lakshmanarao, A.

doi:10.1007/978-981-16-2594-7_53

Cited by 2 publications

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar correlation coefficient based feature selection was also used in Refs. [33,34]. In this case, Tékouabou et al [33] further proposed a classmembership based (CMB) customised classification model to improve performance.…”

Section: Feature Selectionmentioning

confidence: 99%

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning

Kaisar,

Rashid,

Chowdhury

et al. 2024

Big Data Min. Anal.

View full text Add to dashboard Cite

Telemarketing is a well-established marketing approach to offering products and services to prospective customers. The effectiveness of such an approach, however, is highly dependent on the selection of the appropriate consumer base, as reaching uninterested customers will induce annoyance and consume costly enterprise resources in vain while missing interested ones. The introduction of business intelligence and machine learning models can positively influence the decision-making process by predicting the potential customer base, and the existing literature in this direction shows promising results. However, the selection of influential features and the construction of effective learning models for improved performance remain a challenge. Furthermore, from the modelling perspective, the class imbalance nature of the training data, where samples with unsuccessful outcomes highly outnumber successful ones, further compounds the problem by creating biased and inaccurate models. Additionally, customer preferences are likely to change over time due to various reasons, and/or a fresh group of customers may be targeted for a new product or service, necessitating model retraining which is not addressed at all in existing works. A major challenge in model retraining is maintaining a balance between stability (retaining older knowledge) and plasticity (being receptive to new information). To address the above issues, this paper proposes an ensemble machine learning model with feature selection and oversampling techniques to identify potential customers more accurately. A novel online learning method is proposed for model retraining when new samples are available over time. This newly introduced method equips the proposed approach to deal with dynamic data, leading to improved readiness of the proposed model for practical adoption, and is a highly useful addition to the literature. Extensive experiments with real-world data show that the proposed approach achieves excellent results in all cases (e.g., 98.6% accuracy in classifying customers) and outperforms recent competing models in the literature by a considerable margin of 3% on a widely used dataset.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning

Kaisar,

Rashid,

Chowdhury

et al. 2024

Big Data Min. Anal.

View full text Add to dashboard Cite

show abstract

A novel ensemble approach for estimating the competency of bank telemarketing

Guo,

Yao,

Liu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Having a reliable understanding of bank telemarketing performance is of great importance in the modern world of economy. Recently, machine learning models have obtained high attention for this purpose. In order to introduce and evaluate cutting-edge models, this study develops sophisticated hybrid models for estimating the success rate of bank telemarketing. A large free dataset is used which lists the clients’ information of a Portuguese bank. The data are analyzed by four artificial neural networks (ANNs) trained by metaheuristic algorithms, namely electromagnetic field optimization (EFO), future search algorithm (FSA), harmony search algorithm (HSA), and social ski-driver (SSD). The models predict the subscription of clients for a long-term deposit by evaluating nineteen conditioning parameters. The results first indicated the high potential of all four models in analyzing and predicting the subscription pattern, thereby, revealing the competency of neuro-metaheuristic hybrids. However, comparatively speaking, the EFO yielded the most reliable approximation with an area under the curve (AUC) around 0.80. FSA-ANN emerged as the second-accurate model followed by the SSD and HSA with respective AUCs of 0.7714, 0.7663, and 0.7160. Moreover, the superiority of the EFO-ANN is confirmed against several conventional models from the previous literature, and finally, it is introduced as an effective model to be practically used by banking institutions for predicting the likelihood of deposit subscriptions.

show abstract

Improving Efficiency of Machine Learning Model for Bank Customer Data Using Genetic Algorithm Approach

Cited by 2 publications

References 7 publications

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning

A novel ensemble approach for estimating the competency of bank telemarketing

Contact Info

Product

Resources

About