Preprocessing Imbalanced Data: A Systematic Review of Rebalancing Techniques, Quality Standards, and Unresolved Methodological Tensions
Keywords:
class imbalance, data preprocessing, resampling techniques, synthetic minority oversampling, systematic literature review, machine learning quality, imbalanced classificationAbstract
Class imbalance in training data—where minority classes constitute a small fraction of observations—has been treated as a preprocessing problem requiring correction, yet whether rebalancing techniques improve model performance or introduce artifacts remains contested. Existing reviews lack systematic quality assessment of preprocessing studies and fail to distinguish between techniques that alter class distributions versus those that clean data without changing proportions. This systematic review analyzed 118 studies published 2010–2018, applying explicit quality criteria to assess evidence for oversampling, undersampling, synthetic generation, and data cleaning techniques across domains including healthcare, fraud detection, and software defect prediction. Only 2% of studies followed systematic review guidelines; rebalancing techniques demonstrated recall improvements in 60–70% of cases but introduced concept drift in synthetic minority oversampling applications; no consensus exists on when imbalance constitutes a genuine learning obstacle versus a misattributed explanation for poor model architecture. The review identifies three unresolved tensions—rebalancing efficacy versus artifact risk, imbalance as cause versus symptom, and domain-specific versus universal preprocessing strategies—and proposes a decision framework linking preprocessing choice to problem characteristics rather than default application of rebalancing. Future research must distinguish preprocessing effectiveness from model selection effects and establish empirical thresholds for when class imbalance warrants intervention.
References
[1] Abdelhay O, Shatnawi A, Najadat H, Altamimi T. Resampling methods for class imbalance in clinical prediction models: A scoping review protocol. PLoS One. 2025 Nov 3;20(11):e0330050. doi:10.1371/journal.pone.0330050.PMID:41183062;PMCID: PMC12582444.
[2] Osama Abdelhay¹*, Adam Shatnawi², Hassan Najadat², Taghreed Altamimi3 ¹ Department of Data Science and Artificial Intelligence, Princess Sumaya University for Technology, Amman, Jordan ² Department of Computer Science, Jordan University of Science and Technology, Irbid, Jordan 3 College of Engineering and Advanced Computing, Alfaisal University, Riyadh, Saudi Arabia (2025) Resampling Methods for Class Imbalance in Clinical Prediction Models: A Systematic Review and Meta-Regression Protocol.
[3] Carvalho, M., Pinho, A.J. & Brás, S. Resampling approaches to handle class imbalance: a review from a data perspective. J Big Data 12, 71 (2025). https://doi.org/10.1186/s40537-025-01119-4
[4] Lanera C, Berchialla P, Sharma A, Minto C, Gregori D, Baldi I. Screening PubMed abstracts: is class imbalance always a challenge to machine learning? Syst Rev. 2019 Dec 6;8(1):317. doi: 10.1186/s13643-019-1245-8. PMID: 31810495; PMCID: PMC6896747.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6896747/
[5] Barua, S., Islam, M. M., Yao, X., & Murase, K. (2014). MWMOTE—Majority weighted minority oversampling technique for imbalanced data set learning. IEEE Transactions on Knowledge and Data Engineering, 26(2), 405–425. https://doi.org/10.1109/TKDE.2012.232
[6] Batuwita, R., & Palade, V. (2013). Class imbalance learning methods for support vector machines. In H. He & Y. Ma (Eds.), Imbalanced learning: Foundations, algorithms, and applications. Wiley. https://doi.org/10.1002/9781118646106.ch5
[7] He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284. https://doi.org/10.1109/TKDE.2008.239
[8] He, H., & Ma, Y. (Eds.). (2013). Imbalanced learning: Foundations, algorithms, and applications. Wiley. https://doi.org/10.1002/9781118646106
[9] Hoens, T. R., & Chawla, N. V. (2013). Imbalanced datasets: From sampling to classifiers. In H. He & Y. Ma (Eds.), Imbalanced learning: Foundations, algorithms, and applications. Wiley. https://doi.org/10.1002/9781118646106.ch3
[10] Japkowicz, N. (2003). Class imbalance: Are we focusing on the right issue? In Proceedings of the ICML Workshop on Learning from Imbalanced Data Sets (pp. 17–23).
[11] Weiss, G. M. (2013). Foundations of imbalanced learning. In H. He & Y. Ma (Eds.), Imbalanced learning: Foundations, algorithms, and applications. Wiley. https://doi.org/10.1002/9781118646106.ch2
[12] Bunkhumpornpat, C., Sinapiromsaran, K., & Lursinsap, C. (2009). Safe-Level-SMOTE: Safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem. In Advances in knowledge discovery and data mining (pp. 475–482). Springer. https://doi.org/10.1007/978-3-642-01307-2_43
[13] Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
[14] Chawla, N. V., Lazarevic, A., Hall, L. O., & Bowyer, K. W. (2003). SMOTEBoost: Improving prediction of the minority class in boosting. In Knowledge discovery in databases: PKDD 2003 (pp. 107–119). Springer. https://doi.org/10.1007/978-3-540-39804-2_12
[15] Han, H., Wang, W.-Y., & Mao, B.-H. (2005). Borderline-SMOTE: A new over-sampling method in imbalanced data sets learning. In D.-S. Huang, X.-P. Zhang, & G.-B. Huang (Eds.), Advances in intelligent computing (pp. 878–887). Springer. https://doi.org/10.1007/11538059_91
[16] He, H., Bai, Y., Garcia, E. A., & Li, S. (2008). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In 2008 IEEE International Joint Conference on Neural Networks (pp. 1322–1328). IEEE. https://doi.org/10.1109/IJCNN.2008.4633969
[17] Last, F., Douzas, G., & Bacao, F. (2018). Oversampling for imbalanced learning based on K-means and SMOTE. Information Sciences, 465, 1–20. https://doi.org/10.1016/j.ins.2018.06.056
[18] Barua, S., Islam, M. M., Yao, X., & Murase, K. (2014). MWMOTE—Majority weighted minority oversampling technique for imbalanced data set learning. IEEE Transactions on Knowledge and Data Engineering, 26(2), 405–425. https://doi.org/10.1109/TKDE.2012.232
[19] Liu, X.-Y., Wu, J., & Zhou, Z.-H. (2009). Exploratory undersampling for class-imbalance learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 39(2), 539–550. https://doi.org/10.1109/TSMCB.2008.2007853
[20] Seiffert, C., Khoshgoftaar, T. M., Van Hulse, J., & Napolitano, A. (2010). RUSBoost: A hybrid approach to alleviating class imbalance. IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans, 40(1), 185–197. https://doi.org/10.1109/TSMCA.2009.2029559
[21] Batista, G. E. A. P. A., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD Explorations Newsletter, 6(1), 20–29. https://doi.org/10.1145/1007730.1007735
[22] Liu, X.-Y., Wu, J., & Zhou, Z.-H. (2009). Exploratory undersampling for class-imbalance learning. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 39(2), 539–550. https://doi.org/10.1109/TSMCB.2008.2007853
[23] García, V., Sánchez, J. S., & Mollineda, R. A. (2007). An empirical study of the behavior of classifiers on imbalanced and overlapped data sets. In L. Rueda, D. Mery, & J. Kittler (Eds.), Progress in pattern recognition, image analysis and applications (pp. 397–406). Springer.
[24] Krawczyk, B. (2016). Learning from imbalanced data: Open challenges and future directions. Progress in Artificial Intelligence, 5, 221–232. https://doi.org/10.1007/s13748-016-0094-0
[25] Jo, T., & Japkowicz, N. (2004). Class imbalances versus small disjuncts. ACM SIGKDD Explorations Newsletter, 6(1), 40–49. https://doi.org/10.1145/1007730.1007737
[26] Stefanowski, J. (2013). Overlapping, rare examples and data complexity in learning from imbalanced data. In H. He & Y. Ma (Eds.), Imbalanced learning: Foundations, algorithms, and applications. Wiley.
[27]Koziarski, M. (2022). Imbalanced data preprocessing techniques utilizing local data characteristics. Pattern Analysis and Applications, 25, 1–18.
[28] Kraiem, M. S., Sánchez-Hernández, F., & Moreno-García, M. N. (2022). Selecting the suitable resampling strategy for imbalanced data classification regarding dataset properties. Applied Sciences, 12(9), 4478
[29] Davis, J., & Goadrich, M. (2006). The relationship between Precision-Recall and ROC curves. In Proceedings of the 23rd International Conference on Machine Learning (pp. 233–240). ACM. https://doi.org/10.1145/1143844.1143855
[29] Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874.
[30] Flach, P. A. (2019). Performance evaluation in machine learning: The good, the bad, the ugly, and the way forward. In Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 9808–9814. https://doi.org/10.1609/aaai.v33i01.33019808
[31] Saito, T., & Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLOS ONE, 10(3), e0118432. https://doi.org/10.1371/journal.pone.0118432
[32] Tharwat, A. (2021). Classification assessment methods. Applied Computing and Informatics, 17(1), 168–192. https://doi.org/10.1016/j.aci.2018.08.003
[33] He, H., & Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284. https://doi.org/10.1109/TKDE.2008.239
[34] Moscovich, A., & Rosset, S. (2019). On the cross-validation bias due to unsupervised preprocessing. Journal of Machine Learning Research, 20(70), 1–14
[35] Varma, S., & Simon, R. (2006). Bias in error estimation when using cross-validation for model selection. BMC Bioinformatics, 7, 91. https://doi.org/10.1186/1471-2105-7-91
[36] Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th International Joint Conference on Artificial Intelligence (pp. 1137–1143).
[37] Ambroise, C., & McLachlan, G. J. (2002). Selection bias in gene extraction on the basis of microarray gene-expression data. Proceedings of the National Academy of Sciences, 99(10), 6562–6566. https://doi.org/10.1073/pnas.102102699
[38] Cawley, G. C., & Talbot, N. L. C. (2010). On over-fitting in model selection and subsequent selection bias in performance evaluation. Journal of Machine Learning Research, 11, 2079–2107.
[39] Vabalas, A., Gowen, E., Poliakova, N., & Casson, A. J. (2019). Machine learning algorithm validation with a limited sample size. PLOS ONE, 14(7), e0224365. https://doi.org/10.1371/journal.pone.0224365
[40] Aguiar, G., Krawczyk, B., & Cano, A. (2022). A survey on learning from imbalanced data streams: Taxonomy, challenges, empirical study, and reproducible experimental framework. IEEE Access, 10, 105572–105594.
[41] Buda, M., Maki, A., & Mazurowski, M. A. (2018). A systematic study of the class imbalance problem in convolutional neural networks. Neural Networks, 106, 249–259. https://doi.org/10.1016/j.neunet.2018.07.011
[42] Koziarski, M. (2022). Imbalanced data preprocessing techniques utilizing local data characteristics. Pattern Analysis and Applications, 25, 1–18.
[43] Le, T., Lee, M., & Kim, H. (2022). A comprehensive survey of imbalanced learning methods for bankruptcy prediction. IET Communications, 16, 1–20.
[45] Nemade, B., Bharadi, V., Alegavi, S. S., & Marakarkandy, B. (2023). A comprehensive review: SMOTE-based oversampling methods for imbalanced classification techniques, evaluation, and result comparisons. International Journal of Intelligent Systems and Applications in Engineering, 11(10), 1–15.
[46] Cortes, C., Mao, A., Mohri, M., & Zhong, Y. (2025). Balancing the scales: A theoretical and algorithmic framework for learning from imbalanced data. arXiv. https://doi.org/10.48550/arXiv.2502.10381
[47] Kachan, O., Savchenko, A., & Gusev, G. (2025). Simplicial SMOTE: Oversampling solution to the imbalanced learning problem. arXiv. https://doi.org/10.48550/arXiv.2503.03418
[48] Zavitsanos, E., & Paliouras, G. (2026). Focused PU learning from imbalanced data. arXiv. https://doi.org/10.48550/arXiv.2605.14467
Downloads
Published
Data Availability Statement
None
