Class Weighting Technique to Deal with Imbalanced Class Problem in Machine Learning: Methodological Research
Batuhan Bakırarar, Atilla Halil ELHAN
Abstract
Objective: Machine learning algorithms are based upon the assumption that data are balanced and so they do not provide good results in imbalanced datasets. This study aimed to explain the methods to be used for fitting a highly accurate model which better classifies the class of interest in imbalanced datasets with the class having a lower number of samples. Material and Methods: The study was planned as a methodological research. There are several weighting methods to calculate the class weight. This study included 4 most frequently used weighting methods. These are inverse of number of samples, inverse of square root of number of samples, effective number of examples and sample based class weight methods. In our study, 4 different class weighting methods were used on random forest and support vector machine, and it was explained how those methods affected class-based performances and the overall performance. Results: In simulated datasets, the best performance was achieved using the using the inverse of square root of number of samples class weighting method both on random forest and support vector machine. In real dataset, the best performance was achieved using the sample based class weight class weighting method on support vector machine. Conclusion: It was seen that all of the class weighting methods used in both machine learning methods were found to increase the performance of the class where recurrence was seen, therefore increasing the overall performance. It has been seen how effective the class weighting method is in dealing with the class imbalance problem.