Abstract

Cross-domain prediction remains a critical challenge in applications. This work proposes a composite resampling framework to deliver high-fidelity, generalizable predictions from healthcare to financial datasets, bridging domain-specific models and providing robust, scalable predictive performance. In particular, evaluate prediction efficiency using multiple machine learning classification algorithms combined with resampling techniques to address class imbalance, which often degrades accuracy. While these methods have been previously applied to healthcare datasets, it extends their application to financial data, focusing on a bank marketing dataset to predict client subscription tendencies for term deposits. Experimental results demonstrate that integrating resampling techniques with conventional machine learning algorithms significantly improves prediction precision, highlighting the framework’s potential for cross-domain applications. This study contributes to AI-driven decision-making in finance while offering a methodology that can be adapted across other domains with imbalanced data.

References

• J. Han, M. Kamber. “Data mining concept and technology.” Publishing House of Mechanism Industry: 70-72, 2001.
• J. R. Quinlan, “Constructing decision tree.” C4 5, 17-26, 1993.
• M. F. Kabir, S. Aziz, S. Ahmmed, and C. M. Rahman. “Information theoretic SOP expression minimization technique.” Computer and information technology, 2007. iccit 2007. 10th international conference on. IEEE, 2007.
• J. Vanerio, and P. Casas. “Ensemble-learning approaches for network security and anomaly detection.” Proceedings of theWorkshop on Big Data Analytics and Machine Learning for Data Communication Networks. ACM, 2017.
• T. Chen, and C. Guestrin. “Xgboost: A scalable tree boosting system.” Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. ACM, 2016.
• G. Batista, R. C. Prati, and M. C. Monard. “A study of the behavior of several methods for balancing machine learning training data” ACM SIGKDD explorations newsletter 6.1 (2004) : 20 – 29
• N. V. Chawla, K. W. Bowyer, L. O. Hall, W. P. Kegelmeyer. “SMOTE: synthetic minority over-sampling technique.” Journal of artificial intelligence research, 16: 321-357, 2002.
• T. Fawcett, “An introduction to ROC analysis.” Pattern recognition letters 27.8 (2006): 861-874.
• A. Çaliş, A. Boyaci, K Baynal. “Data mining application in banking sector with clustering and classification methods”, Proceedings of the 2015 International Conference on Industrial Engineering and Operations Management, Dubai, United Arab Emirates (UAE), March 3 – 5, 2015, (978-1-4799-6065-1/15©2015 IEEE)
• P. S. Patil, N. V. Dharwadkar, “Analysis of Banking Data Using Machine Learning”, International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC 2017), (978-1-5090-3243-3/17©2017 IEEE)
• B. Valarmathi, T. Chellatamilan, H. Mittal, Jagrit, and Shubham. “Classification of Imbalanced Banking Dataset using Dimensionality Reduction” , Proceedings of the International Conference on Intelligent Computing and Control Systems (ICICCS 2019), IEEE Xplore Part Number: CFP19K34-ART; ISBN:978-1-5386-8113-8
• S. C. K. Tékouabou, P. N. Mata, M. N. Mata, S. C. Gherghina, H. Toulni, J. M. Martins, “AMachineLearning Framework towards Bank Telemarketing Prediction”, https://www.mdpi.com/1911-8074/15/6/269, Journal of Risk and Financial Management, J. Risk Financial Manag. 2022, 15(6), 269; https://doi.org/10.3390/jrfm15060269
• C. Xie, J. Zhang, Y. Zhu, B. Xiong, G. Wang, “How to improve the success of bank telemarketing? Prediction and interpretability analysis based on machine learning”, https://www.sciencedirect.com/science/article/pii/S0360835222008622, Computers & Industrial Engineering, Volume 175, January 2023, 108874
• M. F. Kabir, S. A. Ludwig, “Classification of Breast Cancer Risk Factors Using Several Resampling Approaches”, 2018 17th IEEE International Conference on Machine Learning and Applications, (978-1-5386-6805-4/18/ ©2018 IEEE)
• “UCMachine Learning Repository: Bank Marketing Data Set”, https://archive.ics.uci.edu/ml/datasets/Bank+Marketing, last retrieved: September 2020
• “Binary classification - Wikipedia”, https://en.wikipedia.org/wiki/Binary_classification, last retrieved: September 2020
• “Decision tree - Wikipedia”, https://en.wikipedia.org/wiki/Decision_tree, last retrieved: September 2020
• “Random forest - Wikipedia”, https://en.wikipedia.org/wiki/Random_forest, last retrieved: September 2020
• “Gradient boosting - Wikipedia”, https://en.wikipedia.org/wiki/Gradient_boosting, last retrieved: September 2020
• “The Professionals Point: Advantages of XGBoost Algorithm in Machine Learning”, http://theprofessionalspoint.blogspot.com/2019/03/advantages-of-xgboost-algorithm-in.html, last retrieved: September 2020
• J. Mathew, C. K. Pang, M. Luo, and W. H. Leong “Classification of Imbalanced Data by Oversampling in Kernel Space of Support Vector Machines.” IEEE transactions on neural networks and learning systems, 2017
• “Random Oversampling and Undersampling for Imbalanced Classification”, https://machinelearningmastery.com/random-oversampling-and-undersampling-for-imbalanced-classification/, last retrieved: September 2020
• “Application of Synthetic Minority Over-sampling Technique (SMOTe) for Imbalanced Datasets | by Navoneel Chakrabarty | Towards AI — Multidisciplinary Science Journal | Medium”, https://medium.com/towards-artificial-intelligence/application-of-synthetic-minority-over-sampling-technique-smote-for-imbalanced-data-sets-509ab55cfdaf, last retrieved: September 2020
• B. Tang, and H. He, "ENN:Extended Nearest Neighbor Method for Pattern Recognition", IEEE Computational Intelligence Magazine, vol.10, no.3, pp.52--60, Aug,2015
• “Oversampling and undersampling in data analysis - Wikipedia”, https://en.wikipedia.org/wiki/Oversampling_and_undersampling_in_data_analysis, last retrieved: September 2020
• “Using Under-Sampling Techniques for Extremely Imbalanced Data | by Dr. Dataman | Towards Data Science”, https://towardsdatascience.com/sampling-techniques-for-extremely-imbalanced-data-part-i-under-sampling-a8dbc3d8d6d8, last retrieved: September 2020
• “k-means clustering - Wikipedia”, https://en.wikipedia.org/wiki/K-means_clustering, last retrieved: September 2020
• “Oversampling with SMOTE and ADASYN | Kaggle”, https://www.kaggle.com/residentmario/oversampling-with-smote-and-adasyn, last retrieved: September 2020
• “SMOTE and ADASYN ( Handling Imbalanced Data Set ) | by Indresh Bhattacharyya | Coinmonks | Medium”, https://medium.com/coinmonks/smote-and-adasyn-handling-imbalanced-data-set-34f5223e167, last retrieved: September 2020
• “Interpret all statistics and graphs for Cluster K-Means - Minitab”, https://support.minitab.com/en-us/minitab/18/help-and-how-to/modeling-statistics/multivariate/how-to/cluster-k-means/interpret-the-results/all-statistics-and-graphs, last retrieved: September 2020
• “Accuracy (error rate) Definition | DeepAI”, https://deepai.org/machine-learning-glossary-and-terms/accuracy-error-rate, last retrieved: September 2020