An Approach to Reliably Classify Imbalanced Data

  • Venkatesh Mainalli, Shivraj Deshmukh, Gaurav Bade, Akshay Dhole, Geeta S. Navale


Several real-world data sets have an imbalanced distribution of the instances. Learning from such data sets leads classifier being biased towards the majority class, thereby tending to misclassify the minority class samples. Imbalanced data set can cause negative effect on machine learning’s classification performance. Many attempts are carried on for addressing issue of imbalanced datasets. The data is to be rebalanced by artificial means by oversampling or under sampling to handle the problem of imbalanced data. In this paper authors propose an approach referred as diversifying ensemble technique which can eliminate such drawback & the related work carried out in this domain.