A Survey of Predictive Modeling on Imbalanced Domains
Open accessThe DOI matches its Crossref record; 261 of the 266 references it cites were found in a registry or an index.
Abstract
Many real-world data-mining applications involve obtaining predictive models using datasets with strongly imbalanced distributions of the target variable. Frequently, the least-common values of this target variable are associated with events that are highly relevant for end users (e.g., fraud detection, unusual returns on stock markets, anticipation of catastrophes, etc.). Moreover, the events may have different costs and benefits, which, when associated with the rarity of some of them on the available training data, creates serious problems to predictive modeling techniques. This article presents a survey of existing techniques for handling these important applications of predictive analytics. Although most of the existing work addresses classification tasks (nominal target variables), we also describe methods designed to handle similar problems within regression tasks (numeric target variables). In this survey, we discuss the main challenges raised by imbalanced domains, propose a definition of the problem, describe the main approaches to these tasks, propose a taxonomy of the methods, summarize the conclusions of existing comparative studies as well as some theoretical analyses of some methods, and refer to some related problems within predictive modeling.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Here, techniques such as under-sampling and synthetic data have been found to enhance model performance [16].”
From A Survey of Data Quality Requirements That Matter in ML Development Pipelines (2023) · cites this paper as [16]
In the citing paper
“Earlier trends of opportunistic data collection and post hoc justifications of large datasets are gradually moving towards a requirement for more deliberative data collection methods [35,36], sampling techniques [16] and minimal data architectures [57] to deliver better performance without reducing model accuracy.”
From A Survey of Data Quality Requirements That Matter in ML Development Pipelines (2023) · cites this paper as [16]
Citations
Cites
SMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,411
Classification and Regression Trees.
Gordon, A. D., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984) · Biometrics · doi:10.2307/2530946 · Cited by 23,522
An introduction to ROC analysis
Fawcett, T. (2006) · Pattern Recognition Letters · doi:10.1016/j.patrec.2005.10.010 · Cited by 21,879
He, H., & Garcia, E. A. (2009) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2008.239 · Cited by 10,359
A systematic analysis of performance measures for classification tasks
Sokolova, M., & Lapalme, G. (2009) · Information Processing & Management · doi:10.1016/j.ipm.2009.03.002 · Cited by 7,515
The use of the area under the ROC curve in the evaluation of machine learning algorithms
Bradley, A. P. (1997) · Pattern Recognition · doi:10.1016/s0031-3203(96)00142-2 · Cited by 7,217
Proceedings of the 25th international conference on Machine learning - ICML '08
(2008) · doi:10.1145/1390156 · Cited by 6,680
The relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559
Estimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168 · cited 1×
“Developments made in this context include one-class SVMs (e.g., Sch¨olkopf et al. [2001], Manevitz and Yousef [2002], Raskutti and Kowalczyk [2004], Zhuang and Dai [2006a, 2006b], and Lee and Cho [2006]) and the use of an autoencoder (or autoassociator) (e.g., Japkowicz et al. [1995] and Japkowicz…”
Method
Research works printed but not linked: 52
- Akbani Rehan, 2004, Machine Learning: ECML
- Alejo Roberto, 2013, Rosa Maria Valdovinos, and J. Horacio Pacheco-Sánchez
- Alejo Roberto, 2007, Ramón Alberto Mollineda, and José Salvador Sánchez.
- Eleuterio Roberto Alejo, 2011, Vicente García Jiménez, and Rosa María Valdovinos Rosas.
- Attenberg Josh, Imbalanced Learning: Foundations
- Bi Jinbo, Proc. of the 20th Int. Conf. on Machine Learning. 43--50
- Branco Paula, Re-sampling Approaches for Regression Tasks under Imbalanced Domains. Master's thesis. Dept. Computer Science
- Breiman Leo, 1984, Stone
- Chawla Nitesh V., 2003, Bowyer
- Chen Chao, 2004, Using random forest to learn imbalanced data
- Chyi Yu-Meei, 2003, Department of Information Management
- Cieslak David A., 2008, Chawla
- Doucette John, 2008, Heywood
- Drummond Chris, Workshop on Learning from Imbalanced Datasets II, 11
- Elkan Charles, 2001, IJCAI'01: Proc. of 17th Int. Joint Conf. of Artificial Intelligence, 1
- Ferri César, 2005, Proceedings of the Second Workshop on ROC Analysis in Machine Learning. 33--40
- Ferri César, Proceedings of the 28th International Conference on Machine Learning (ICML-11)
- Forman George, 2004, Knowledge Discovery in Databases: PKDD
- He Haibo, 2008, IEEE International Joint Conference on Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE, 1322--1328
- Holte Robert C., IJCAI, 89
- 10.5555/1681514.1682710 · doi:10.5555/1681514.1682710
- Japkowicz Nathalie, 2000, AAAI Workshop on Learning from Imbalanced Data Sets, 68
- Japkowicz Nathalie, 2003, Workshop on Learning from Imbalanced Data Sets II, 1723
- Japkowicz Natalie, Imbalanced Learning: Foundations
- Jeatrakul Piyasak, 2010, Kok Wai Wong, and Chun Che Fung
- Joshi Mahesh V., Proceedings IEEE International Conference on Data Mining, 2001. ICDM 2001. IEEE, 257--264
- Kubat Miroslav, 1997, Proc. of the 14th Int. Conf. on Machine Learning. Morgan Kaufmann, 179--186
- Liu Alexander, 2007, Martin
- Liu Wei, 2010, Chawla
- Maloof Marcus A., 2003, ICML-2003 Workshop on Learning from Imbalanced Data Sets II, 2
- Mani Inderjeet, 2003, Proceedings of Workshop on Learning from Imbalanced Datasets.
- 10.5555/1314498.1314514 · doi:10.5555/1314498.1314514
- Pearson Ronald, 2003, Proceedings of the ICML, 3
- Provost Foster J, 1998, ICML'98: Proc. of the 15th Int. Conf. on Machine Learning. Morgan Kaufmann Publishers, 445--453
- Raeder Troy, 2012, Chawla
- Rita, 2003, Ribeiro and Luís Torgo
- Rijsbergen Cornelis V., 1979, Information Retrieval. Dept. of Computer Science
- Sánchez-Crisostomo Juan Pablo, 2014, Rosa María Valdovinos, and J. Horacio Pacheco-Sánchez
- Sánchez-Monedero Javier, 2013, Pedro Antonio Gutiérrez, and Cesar Hervás-Martínez
- Songwattanasiri Panote, 2010, Proceedings of the Annual International Conference on Computer Science Education: Innovation and Technology
- Torgo Luís, 2003, Ribeiro
- Torgo Luís, 2007, Ribeiro
- Wagstaff Kiri L., 2013, Gilmore
- Wallace Byron C., 2011 IEEE 11th International Conference on Data Mining (ICDM). IEEE, 754--763
- Wang Heng, 2015, Concept drift detection for imbalanced stream data. arXiv Preprint arXiv:1504.01044 · arXiv
- Wang Xiaoguang, Advances in Artificial Intelligence
- Weiss Gary M., Data Mining
- Weiss Gary M., Imbalanced Learning: Foundations
- Cheng, Proceedings of the 7th Australasian Data Mining Conference-Volume 87
- Wu Gang, ICML 2003 Workshop on Learning from Imbalanced Data Sets II
- 10.5555/951949.952181 · doi:10.5555/951949.952181
- Zhang Dongmei, 2011, A novel improved SMOTE resampling algorithm based on fractal, J. Comput. Inform. Syst., 7, 2204
Cited by
Items 401–500 of 1,000
Bashir, K., Li, T., Yohannese, C. W., & Yahaya, M. (2019) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-179459 · Cited by 17
Imbalanced Data Classification Using Improved Clustering Algorithm and Under-Sampling Method
Cao, L., & Shen, H. (2019) · International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT) · doi:10.1109/pdcat46702.2019.00071 · Cited by 15
“However, the data obtained in real life often lead to imbalance of sample size, overlap between the classes and noise interference, which makes the traditional classifier cannot achieve the desired results [5].”
BackgroundAsim, Y., Malik, A. K., Raza, B., Shahid, A. R., & Qamar, N. (2020) · IEEE Access · doi:10.1109/access.2020.3048610 · Cited by 15
“…moved us towards a different view of the prescribed problem in terms of imbalanced data classification techniques and performance measures, where imbalanced data problem indicates that important cases (positive instances of target output class) are few or rare in the training dataset [22], [23].”
BackgroundAktaş, S., Alemdar, H. O., & Ergüt, S. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.107742 · Cited by 22
FedVAE: Communication-Efficient Federated Learning With Non-IID Private Data
Yang, H., Ge, M., Xiang, K., Bai, X., & Li, H. (2023) · IEEE Systems Journal · doi:10.1109/jsyst.2023.3274197 · Cited by 22
“to discriminative modeling because most classifiers are based on the assumption that each class has roughly an equal number of samples [5], [6], [7].”
The Jeopardy of Learning from Over-Sampled Class-Imbalanced Medical Datasets
Hassanat, A. B. A., Altarawneh, G., Alkhawaldeh, I. M., Alabdallat, Y. J., Atiya, A. F., Abujaber, A. A., & Tarawneh, A. S. (2023) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc58397.2023.10218211 · Cited by 14
Banulescu‐Radu, D., & Yankol‐Schalck, M. (2023) · Journal of Risk & Insurance · doi:10.1111/jori.12452 · Cited by 28
MLcps: machine learning cumulative performance score for classification problems
Akshay, A., Abedi, M., Shekarchizadeh, N., Burkhard, F. C., Katoch, M., Bigger-Allen, A., Adam, R. M., Monastyrskaya, K., & Gheinani, A. H. (2022) · GigaScience · doi:10.1093/gigascience/giad108 · Cited by 16
“Comparison of different metric scores for a large number of models to identify the best-performing model is labour-intensive, and this process is prone to user preference bias [6].”
Diamantis, D. E., Gatoula, P., Koulaouzidis, A., & Iakovidis, D. K. (2023) · IEEE Access · doi:10.1109/access.2024.3366801 · Cited by 23
“…(AUC) measure [59], was computed to assess the performance of the trained classification models, because, unlike other measures, such as accuracy, sensitivity and specificity, which are obtained using only a single decision threshold, it is insensitive to imbalanced class distributions [59], [60].”
Deep learning-based automatic analysis of legal contracts: a named entity recognition benchmark
Aejas, B., Belhi, A., Zhang, H., & Bouras, A. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09869-7 · Cited by 17
“To address the issue of significant class imbalance in the dataset, where there is a much larger proportion of ‘O’ tags compared to other tags, we conducted Random Under-Sampling (RUS) [30], which involved reducing the number of sentences containing any NE tags.”
From fault detection to anomaly explanation: A case study on predictive maintenance
da Gama, J. M. P., Ribeiro, R. P., Mastelini, S. M., Davari, N., & Veloso, B. (2024) · Journal of Web Semantics · doi:10.1016/j.websem.2024.100821 · Cited by 14
Self-citationZhu, W., Lü, C., & Chen, X. M. (2024) · Transportmetrica B Transport Dynamics · doi:10.1080/21680566.2024.2358211 · Cited by 14
“However,randomlyduplicatingminoritysampleshasahighrisk of overfitting under high over-sampling rates (Branco et al., 2016).”
Attenuating majority attack class bias using hybrid deep learning based IDS framework
Narayan, K. G. R., Ganesula, R., Somasekhar, T., Mookherji, S., Odelu, V., Prasath, R., & Reddy, A. G. (2024) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2024.103954 · Cited by 21
Utilizing attack enumerations to study SDN/NFV vulnerabilities
Dang, Q.-V., & François, J. (2018) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft.2018.8459961 · Cited by 15
“We also applied sampling preprocessing techniques, i.e. over-sampling, under-sampling and SMOTE [27] to further improve the predictive power of the classifier.”
MethodCSSG: A cost‐sensitive stacked generalization approach for software defect prediction
Eivazpour, Z., & Keyvanpour, M. R. (2021) · Software Testing Verification and Reliability · doi:10.1002/stvr.1761 · Cited by 16
“Meanwhile, the algorithm-level methods straight learn the imbalanced data distribution from the classes, such as one class learning classifications, and ensemble learning [23] (for more details, see other studies [13,19,20,23,24]).”
MethodNg, W. W. Y., Liu, Z., Zhang, J., & Pedrycz, W. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107178 · Cited by 14
Accurate identification of RNA D modification using multiple features
Dou, L., Zhou, W., Zhang, L., Xu, L., & Han, K. (2021) · RNA Biology · doi:10.1080/15476286.2021.1898160 · Cited by 14
Smote vs. Random Undersampling for Imbalanced Data - Car Ownership Demand Model
Chaipanha, W., & Kaewwichian, P. (2022) · Communications - Scientific letters of the University of Zilina · doi:10.26552/com.c.2022.3.d105-d115 · Cited by 21
“In other words, the minority class may be misclassified as the majority class [7-8].”
BackgroundTransfer and share: semi-supervised learning from long-tailed data
Wei, T., Liu, Q., Shi, J.-X., Tu, W.-W., & Guo, L.-Z. (2022) · Machine Learning · doi:10.1007/s10994-022-06247-z · Cited by 20
“Since the test set remains balanced, overall accuracy, minority-class accuracy, and Geometric Mean scores (GM) (Branco et al., 2016) with class-wise sensitivity are three main metrics to validate the proposed method.”
SaR: Self-adaptive Refinement on Pseudo Labels for Multiclass-Imbalanced Semi-supervised Learning
Lai, Z., Wang, C., Cheung, S.-C. S., & Chuah, C. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00454 · Cited by 29
“5% on the geometric mean (GM) score of class-wise accuracies [6] respectively.”
BackgroundMethodEnsembles of cost-diverse Bayesian neural learners for imbalanced binary classification
Lázaro, M., Herrera, F., & Figueiras-Vidal, A. R. (2020) · Information Sciences · doi:10.1016/j.ins.2019.12.050 · Cited by 14
Mathew, T., Niyas, S., Johnpaul, C. I., Kini, J. R., & Rajan, J. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2022.103657 · Cited by 13
Effect of Missing Data Types and Imputation Methods on Supervised Classifiers: An Evaluation Study
Gabr, M. I., Helmy, Y., & Elzanfaly, D. S. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7010055 · Cited by 23
ImbalancedLearningRegression - A Python Package to Tackle the Imbalanced Regression Problem
Wu, W., Kunz, N., & Branco, P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26422-1_48 · Cited by 13
“A model trained on an imbalanced data set cannot focus on the important regions and thus is not able to predict well the most important rare cases [2].”
BackgroundSelf-citationVicente, D. J., Salazar, F., López-Chacón, S. R., Soriano, C., & Vide, J. M. (2023) · Atmospheric Pollution Research · doi:10.1016/j.apr.2023.101999 · Cited by 15
Solving imbalanced learning with outlier detection and features reduction
Lusito, S., Pugnana, A., & Guidotti, R. (2023) · Machine Learning · doi:10.1007/s10994-023-06448-0 · Cited by 27
ECG data enhancement method using generate adversarial networks based on Bi-LSTM and CBAM
Zhou, F., & Li, J. (2024) · Physiological Measurement · doi:10.1088/1361-6579/ad2218 · Cited by 13
Multi-Class Imbalanced Data Classification: A Systematic Mapping Study
Wang, Y., Rosli, M. M., Musa, N., & Li, F. (2024) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.7206 · Cited by 13
Review of Stuck Pipe Prediction Methods and Future Directions
Montes, A. C., Ashok, P., & van Oort, E. (2025) · SPE Journal · doi:10.2118/220725-pa · Cited by 22
Imbalanced Classification with Multiple Classes
Fernández, A., García, S., Galar, M., Prati, R. C., Krawczyk, B., & Herrera, F. (2018) · Springer eBooks · doi:10.1007/978-3-319-98074-4_8 · Cited by 18
Subclass-based semi-random data partitioning for improving sample representativeness
Liu, H., Chen, S., & Cocea, M. (2018) · Information Sciences · doi:10.1016/j.ins.2018.11.002 · Cited by 14
“It has been a very popular strategy to adopt machine learning approaches for the purposes of knowledge discovery (e.g., [11, 39, 43]) and predictive modelling (e.g., [1, 32, 33]), which involves the training and testing stages.”
MethodImbalanced Data Classification Based on Feature Selection Techniques
Ksieniewicz, P., & Woźniak, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03496-2_33 · Cited by 13
CSS : Handling imbalanced data by improved clustering with stratified sampling
Cao, L., & Shen, H. (2020) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6071 · Cited by 17
“The improved CFSFDP algorithm implementation steps are as follows: Step 1: Calculate the cluster center weight γ i of each point according to Formula (5); Step 2: Sort sample points according to non-increasing order of γ i; Step 3: Calculate ki−1 1 and k1 i , determine the turning point according to Formula (7); Step…”
MethodAcar, E., Ertuğrul, Ö. F., Aldemir, E., & Öztekin, A. (2022) · Journal of Plant Diseases and Protection · doi:10.1007/s41348-022-00583-x · Cited by 14
“To even the unbalanced data, both oversampling by utilizing augmentation techniques and undersampling techniques can be applied to the image classes (Branco et al. 2016; Chawla et al. 2005).”
MethodSupervised Multivariate Kernel Density Estimation for Enhanced Plasma Etching Endpoint Detection
Choi, J., Kim, B., Im, S., & Yoo, G. (2022) · IEEE Access · doi:10.1109/access.2022.3155513 · Cited by 16
“An F1-score close to 1 represents good performance, whereas a zero F1-score fails in classification [42].”
BackgroundZhu, H., Ao, C., Ding, Y., Hao, H., & Yu, L. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms23063044 · Cited by 13
“The hybrid sampling method, Synthetic Minority Oversampling Technique and Edited Nearest Neighbors (SMOTEEEN) [31,32], was adopted to solve the data imbalance problem.”
MethodBoundary-Focused Generative Adversarial Networks for Imbalanced and Multimodal Time Series
Lee, H. K., Lee, J., & Kim, S. B. (2022) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3182327 · Cited by 13
Xu, Q., Xu, C., & Wang, J. (2022) · Autonomous Intelligent Systems · doi:10.1007/s43684-022-00041-3 · Cited by 13
“The data level is more convenient, because it does not need to modify the traditional model, and the method of processing the data set can be combined with the existing prediction model [24].”
MethodKUALA: a machine learning-driven framework for kinase inhibitors repositioning
Simone, G. D., Sardina, D. S., Gulotta, M. R., & Perricone, U. (2022) · Scientific Reports · doi:10.1038/s41598-022-22324-8 · Cited by 14
Designing a supervised feature selection technique for mixed attribute data analysis
Jeong, D. H., Jeong, B. K., Leslie, N., Kamhoua, C., & Ji, S.-Y. (2022) · Machine Learning with Applications · doi:10.1016/j.mlwa.2022.100431 · Cited by 16
Hybrid SNN-based Privacy-Preserving Fall Detection using Neuromorphic Sensors
Prasad, S. S., Mehta, N. K., Kumar, H., Banerjee, A., Saurav, S., & Singh, S. K. (2023) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/3627631.3627650 · Cited by 18
“When assessing a model’s performance using accuracy in the presence of such class imbalance, the issue of the accuracy paradox arises, as noted by Branco et al. [6].”
MethodFernández, A., García, S., Galar, M., Prati, R. C., Krawczyk, B., & Herrera, F. (2018) · Springer eBooks · doi:10.1007/978-3-319-98074-4_6 · Cited by 13
A Bayes Risk Minimization Machine for Example-Dependent Cost Classification
Lázaro, M., & Figueiras-Vidal, A. R. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2913572 · Cited by 11
“the influence of critical samples and/or emphasizing unimportant instances [20].”
BackgroundGuo, S., Dong, J., Li, H., & Wang, J. (2021) · Journal of Software Evolution and Process · doi:10.1002/smr.2362 · Cited by 14
An interpretable and generalised machine learning model for predicting flotation performance
Lartey, C., Asamoah, R. K., Greet, C., Zanin, M., & Liu, J. (2025) · Minerals Engineering · doi:10.1016/j.mineng.2025.109492 · Cited by 14
Imbalanced classification with label noise: A systematic review and comparative analysis
Brishti, F. J., Zhang, F., Mohammed, S. S., Bai, L., Wu, F., & Chen, B. (2025) · ICT Express · doi:10.1016/j.icte.2025.09.011 · Cited by 27
Morgenroth, J., Unterlaß, P. J., Sapronova, A., Khan, U. T., Perras, M. A., Erharter, G. H., & Marcher, T. (2022) · Geomechanics and Tunnelling · doi:10.1002/geot.202200047 · Cited by 12
Fay, L., Cobos, E., Yang, B., Gatidis, S., & Küstner, T. (2023) · IEEE Access · doi:10.1109/access.2023.3289397 · Cited by 19
“Another approach is to address the class imbalance by oversampling the minority class with replacement [45] or by incorporating data from different sources to improve generalization [46].”
Analysis of contextualized intensity in Men’s elite handball using graph-based deep learning
Bassek, M., Raabe, D., Banning, A., Memmert, D., & Rein, R. (2023) · Journal of Sports Sciences · doi:10.1080/02640414.2023.2268366 · Cited by 13
“A weighted cross-entropy loss was used as the loss function to account for the heavy class imbalance and prevent the network from ignoring the underrepresented CATT (Branco et al., 2017).”
MethodProperties of Fairness Measures in the Context of Varying Class Imbalance and Protected Group Ratios
Brzeziński, D., Stachowiak, J., Stefanowski, J., Szczęch, I., Susmaga, R., Aksenyuk, S., Ivashka, U., & Yasinskyi, O. (2024) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3654659 · Cited by 23
“Such a study would be valuable in guiding machine learning practitioners on the use of fairness measures, as many real-world datasets are naturally imbalanced [5].”
Dar, A. W., & Farooq, S. U. (2024) · Innovations in Systems and Software Engineering · doi:10.1007/s11334-024-00571-4 · Cited by 16
“The data re-sampling techniques are the prevalent and most commonly used techniques because of their less complexity and easy implementation on any classifier [17].”
Chen, X.-Y., Lu, W.-T., Zhang, D., Tan, M., & Qin, X. (2024) · Scientific Reports · doi:10.1038/s41598-024-78797-2 · Cited by 14
Facial-expression recognition based on a low-dimensional temporal feature space
Abdallah, T. B., Guermazi, R., & Hammami, M. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5354-x · Cited by 12
“Using the subjectindependent 10-cross validation, we determine the best combination of d ∈ [1, 4] and C ∈ [0, 8] for the polynomial kernel, and of C ∈ [0, 8] and γ ∈ [0.”
MethodBasu, A., Das, S., Mullick, S. S., & Das, S. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3149971 · Cited by 14
“Therefore, if a training dataset contains class imbalance then that should be explicitly addressedbydata-level,algorithm-level,orhybridmethods[10].”
BackgroundResampling Techniques for Materials Informatics: Limitations in Crystal Point Groups Classification
Alsaui, A. A., Alghofaili, Y. A., Alghadeer, M., & Alharbi, F. H. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00666 · Cited by 14
Occupancy estimation in smart buildings using predictive modeling in imbalanced domains
Guo, J., Amayri, M., Najar, F., Fan, W., & Bouguila, N. (2022) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-022-04359-x · Cited by 14
“Imbalanced classes distributions cause serious problems to predictive modelling approaches (Branco et al. 2016).”
BackgroundMethodInfluentialDeepBSRPred: deep learning-based binding site residue prediction for proteins
Nikam, R., Yugandhar, K., & Gromiha, M. M. (2022) · Amino Acids · doi:10.1007/s00726-022-03228-3 · Cited by 12
“Binding residue prediction is highly imbalanced; hence, F1 score and MCC are better indicators to evaluate the performance of the method (Branco and Torgo 2016; Saito and Rehmsmeier 2015; Sun et al. 2009).”
BackgroundThe impact of class imbalance techniques on crashing fault residence prediction models
Zhao, K., Zhou, X., Yan, M. L., Zhang, T., Xue, L., Fan, M. Y., & Keung, J. (2023) · Empirical Software Engineering · doi:10.1007/s10664-023-10294-y · Cited by 13
“• Bag ging ( Bag ) (Breiman 1996) randomly selects several instance subsets by means of putting back instances in each sampling process.”
BackgroundGao, J., Lee, C. D., Özbay, K. M. A., Zuo, F., & Chippendale, T. L. (2023) · Transportation Research Interdisciplinary Perspectives · doi:10.1016/j.trip.2023.100815 · Cited by 12
Wang, H., Tucker, W. J., Jonnagaddala, J., Schutte, A. E., Jalaludin, B. B., Liaw, S., Rye, K., Wong, R. K., & Ong, K. L. (2023) · International Journal of Cardiology · doi:10.1016/j.ijcard.2023.05.030 · Cited by 14
Hlosta, M., Zdráhal, Z., & Zendulka, J. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.07.021 · Cited by 12
“The most recent survey that covers many of the issues and also provides a taxonomy of the solutions comes from Branco et al. [12].”
Zhang, J., & Ng, W. W. Y. (2018) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2018.00078 · Cited by 12
“Class imbalance is a common issue in many real-world applications, such as diagnosis of rare diseases, forecasting rare extreme returns in financial markets [1], fault diagnosis, and anomaly detection [2].”
BackgroundRodríguez‐González, A., Tuñas, J. M., Santamaría, L. P., Peces-Barba, D. F., Menasalvas, E., Jaramillo, A., Cotarelo, M., Fernández, A. J. C., Arce, A., & de Miguel, Á. G. (2020) · Applied Sciences · doi:10.3390/app10249019 · Cited by 13
“Learning from imbalance data is still a challenge for machine learning methods nowadays [57].”
BackgroundResampling methods for class imbalance in clinical prediction models: A scoping review protocol
Abdelhay, O., Shatnawi, A., Najadat, H., & Altamimi, T. (2025) · PLoS ONE · doi:10.1371/journal.pone.0330050 · Cited by 20
Sharmin, S., Ivan, J. N., Marsh, K. L., Paxton, A., & Tucker, A. (2022) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981221108985 · Cited by 12
Hwang, K., Kang, W., & Jung, Y.-G. (2023) · Environmental and Ecological Statistics · doi:10.1007/s10651-023-00573-8 · Cited by 11
Harneshing the Potential of EEG in Neuromarketing with Deep Learning and Riemannian Geometry
Georgiadis, K., Kalaganis, F. P., Oikonomou, V. P., Nikolopoulos, S., Laskaris, N., & Kompatsiaris, I. Y. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43075-6_3 · Cited by 11
Boukouvalas, Z., & Shafer, A. (2023) · Annual Review of Statistics and Its Application · doi:10.1146/annurev-statistics-040622-033806 · Cited by 15
A Systematic Literature Review of Novelty Detection in Data Streams: Challenges and Opportunities
Gaudreault, J.-G., & Branco, P. (2024) · ACM Computing Surveys · doi:10.1145/3657286 · Cited by 23
“…AUC) is another common way of measuring performance in imbalanced domains, which was also adapted for ND, and consists of plotting the True Positive Rate ( TPR ) against the False Positive Rate ( FPR ) (cf. Table 5) for different decision thresholds and then computing its area under the curve [24].”
MethodSelf-citationStroke Prediction Using Deep Learning and Transfer Learning Approaches
Shih, D., Wu, Y.-H., Wu, T.-W., Chu, H.-Y., & Shih, M. (2024) · IEEE Access · doi:10.1109/access.2024.3429157 · Cited by 13
“In this study, the random under-sampling method is adopted to deal with category imbalance, which considers the false positive rate (FPR) and false negative rate (FNR), because they play an essential role in medical applications [16].”
MethodBERTGuard: Two-Tiered Multi-Domain Fake News Detection with Class Imbalance Mitigation
Alnabhan, M. Q., & Branco, P. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8080093 · Cited by 16
Self-citationEvaluating Difficulty of Multi-class Imbalanced Data
Lango, M., Napierała, K., & Stefanowski, J. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-60438-1_31 · Cited by 11
“On one hand, several new specialized algorithms as well as data preprocessing methods have been developed; see their reviews in [3, 5].”
MethodPredicting No-show Medical Appointments Using Machine Learning
Alshaya, S., McCarren, A. L., & Al‐Rasheed, A. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-36365-9_18 · Cited by 12
Li, C.-C., Wu, M., Sun, Y.-C., Chen, H., Wu, H., Fang, S.-T., Chung, W., Guo, W., & Lu, H. H. (2021) · Scientific Reports · doi:10.1038/s41598-021-99984-5 · Cited by 11
Sung, S., Sung, K., Pan, R., Lee, P.-J., & Hu, Y. (2022) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2022.941237 · Cited by 11
“Because class imbalance might influence the classification performance, we experimented with resampling methods to maintain the ratio of majority and minority classes as 1:1, 2:1, or 3:1 (38).”
MethodThe determinants of investment fraud: A machine learning and artificial intelligence approach
Lokanan, M. E. (2022) · Frontiers in Big Data · doi:10.3389/fdata.2022.961039 · Cited by 14
“In machine learning, the loss of data can make the decision boundary between the minority (no-fraud) and majority (fraud) class harder to learn from and leads to poor generalization of the validation set (Branco et al., 2016).”
BackgroundKNNGAN: an oversampling technique for textual imbalanced datasets
Madani, M., Motameni, H., & Mohamadi, H. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-022-04851-3 · Cited by 12
Improving Imbalanced Machine Learning with Neighborhood-Informed Synthetic Sample Placement
Nasir, M., Dağ, A., Simsek, S., Ivanov, A., & Oztekin, A. (2022) · Journal of Management Information Systems · doi:10.1080/07421222.2022.2127453 · Cited by 16
“Low density in the data space and small sample sizes are often hallmarks of imbalanced datasets [52], leading to difficulties in learning rare patterns in the data space [7].”
BackgroundImbalanced Multimodal Attention-Based System for Multiclass House Price Prediction
Li, Y., Branco, P., & Zhang, H. (2022) · Mathematics · doi:10.3390/math11010113 · Cited by 16
Self-citationWei, S., Sun, Z., Wang, Z., Liao, F., Li, Z., & Mi, H. (2023) · Applied Sciences · doi:10.3390/app13053177 · Cited by 17
“In contrast, the class imbalance problem has received extensive attention and discussion in the fields of computer vision, speech, and text [13,14,16,35,36].”
BackgroundCost-Sensitive Ensemble Learning for Highly Imbalanced Classification
Johnson, J. M., & Khoshgoftaar, T. M. (2022) · International Conference on Machine Learning and Applications · doi:10.1109/icmla55696.2022.00225 · Cited by 11
“We use the AUPRC metric because it is more sensitive to false positives than AUC, and it has been shown to be more informative than the AUC metric when data is highly imbalanced [39].”
BackgroundMethodRajagopalan, S., Singh, J., & Purohit, A. (2023) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-023-00920-w · Cited by 12
“There are a few ways to overcome class imbalance issues, mainly classified under data level, algorithm level, cost-sensitive methods, and hybrid level approach (ensembled learning) [26, 35–37].”
Model-Free-Communication Federated Learning: Framework and application to Precision Medicine
Falco, I. D., Cioppa, A. D., Koutný, T., Scafuri, U., & Tarantino, E. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105416 · Cited by 13
Research on bank credit default prediction based on data mining algorithm
Li, Y. (2018) · The International Journal of Social Sciences and Humanities Invention · doi:10.18535/ijsshi/v5i6.09 · Cited by 11
“Where TP is the number of true positives, TN is the number of true negatives, FP is the number of false positives, and the number of false negatives[12,13].”
BackgroundPrioritizing Ground‐Motion Validation Metrics Using Semisupervised and Supervised Learning
Khoshnevis, N., & Taborda, R. (2018) · Bulletin of the Seismological Society of America · doi:10.1785/0120180056 · Cited by 11
An RBM Anomaly Detector for the Cloud
Monni, C., Pezzè, M., & Prisco, G. (2019) · IEEE International Conference on Software Testing, Verification and Validation (ICST) · doi:10.1109/icst.2019.00024 · Cited by 15
Tehrani, S. S. M., Zarvani, M., Amiri, P., Azmi, R., Ghods, Z., Nourozi, N., Raoufi, M., Safavi‐Naini, S. A. A., Soheili, A., Abolghasemi, S., et al. (2023) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-023-02344-8 · Cited by 11
“In fact, the later measures may not be reliable criteria when classification is performed on un-balanced data or when data is not normally distributed [62, 63].”
BackgroundRana, P., Fischer, H. W., Coleman, E. A., & Fleischman, F. D. (2024) · Ecology and Society · doi:10.5751/es-14696-290132 · Cited by 12
FAST-GO: Fast, Accurate, and Scalable Hardware Trojan Detection using Graph Convolutional Networks
Imangholi, A., Hashemi, M., Momeni, A., Mohammadi, S., & Carlson, T. E. (2024) · International Symposium on Quality Electronic Design (ISQED) · doi:10.1109/isqed60706.2024.10528759 · Cited by 15
“According to previous work [34], using accuracy is not appropriate when considering imbalanced datasets.”
MethodRajagopalan, S., Purohit, A., & Singh, J. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad5b7d · Cited by 11
“According to research findings [68–73], accuracy was the only performance parameter utilized to identify rotor mass imbalance.”
Self-attention CNN based indoor human events detection with UWB radar
Pan, K., Zhu, W., & Hasannezhad, M. (2024) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2024.107090 · Cited by 10
Hacılar, H., AYDIN, Z., & Güngör, V. Ç. (2024) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.55730/1300-0632.4091 · Cited by 10
Quantification of Data Imbalance
Wibbeke, J., Rohjans, S., & Rauh, A. (2025) · Expert Systems · doi:10.1111/exsy.13840 · Cited by 11
“(Torgo and Ribeiro 2007; Ribeiro 2011; Branco, Torgo, and Ribeiro 2016) proposed a relevance function 𝜙 ( Y ) by splitting the target variable Y into quantiles and calculating the relavance using a sigmoid-based function and the parameters of the inter-quantile range.”
InfluentialMyo‐Guide: A Machine Learning‐Based Web Application for Neuromuscular Disease Diagnosis With MRI
Verdú-Díaz, J., Bolano-Diaz, C., Gonzalez-Chamorro, A., Fitzsimmons, S., Warman‐Chardon, J., Kocak, G., Mucida‐Alvim, D., Smith, I. C. P., Vissing, J., Poulsen, N. S., et al. (2025) · Journal of Cachexia Sarcopenia and Muscle · doi:10.1002/jcsm.13815 · Cited by 15
Enhancing AI for citation screening in literature reviews: Improving accuracy with ensemble models
Zhang, Z., Nezhad, M. J. M., Gupta, P., Zolnour, A., Azadmaleki, H., Topaz, M., & Zolnoori, M. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.106035 · Cited by 14
Optimising e-commerce customer satisfaction with machine learning
Wong, A.-N., & Marikannan, B. P. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1712/1/012044 · Cited by 10
“[21, 22, 23].”
Zhou, Y., Hong, S., Shang, J., Wu, M., Wang, Q., Li, H., & Xie, J. (2020) · Sensors · doi:10.3390/s20247307 · Cited by 10
Yörük, E., Hürriyetoğlu, A., Duruşan, F., & Yoltar, Ç. (2021) · American Behavioral Scientist · doi:10.1177/00027642211021630 · Cited by 11
“We find that the random data is in a position to benefit the most from approaches that oversample the positive class for handling imbalanced data (Branco et al., 2016).”
BackgroundRecession forecasting with high‐dimensional data
Nevasalmi, L. (2021) · Journal of Forecasting · doi:10.1002/for.2823 · Cited by 10
Undersampling of approaching the classification boundary for imbalance problem
Jiang, L., Yuan, P., Liao, J., Zhang, Q., Liu, J., & Li, K. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7586 · Cited by 11
Metadata
- Authors
- Branco, P., Torgo, L., & Ribeiro, R. P.
- Affiliations
- Universidade do Porto (PT)
- LIAAD-INESC TEC, DCC-Faculty of Sciences, University of Porto, Porto, Portugal
- Venue
- ACM Computing Surveys
- Published
- 2016-08-13
- Volume
- 49
- Issue
- 2
- Pages
- 1-50
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W2490420619
- Semantic Scholar
- 736018160f8e6f6bd9b2a9101cd13ee67e573097
- Cited by
- 1,129
- References
- 266
- Citations by year
- 2026: 101 · 2025: 113 · 2024: 167 · 2023: 167 · 2022: 176 · 2021: 137 · 2020: 96 · 2019: 72 · 2018: 60 · 2017: 37 · 2016: 3
- FWCI
- 47.12
- Type
- journal article
- Language
- en
- Open access
- Locations
- ACM Computing Surveys (publishedVersion)
- Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) (submittedVersion, other-oa)
- Funders
- North Portugal Regional Operational Programme (Project NORTE-07-0124-FEDER-000059)
- European Regional Development Fund (POCI-01-0145-FEDER-006961)
- Fundação para a Ciência e a Tecnologia (PD/BD/105788/2014, SFRH/BSAB/113896/2015)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Imbalanced Data Classification Techniques
- Social Sciences › Business, Management and Accounting › Marketing › Customer churn and segmentation
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Keywords
- class imbalance, predictive modeling, rare event prediction, cost-sensitive learning, classification, regression analysis, fraud detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.