A Study imbalance handling by various data sampling methods in binary classification

TL;DR

This paper explores various data sampling techniques to address class imbalance in binary classification, demonstrating their impact on model performance through experiments on a Kaggle dataset.

Contribution

It provides a comparative analysis of over-sampling and under-sampling methods for handling data imbalance in binary classification tasks.

Findings

Sampling methods improve class balance and model accuracy

Over-sampling and under-sampling have different effects on performance

The study highlights gaps for future research in imbalance handling

Abstract

The purpose of this research report is to present the our learning curve and the exposure to the Machine Learning life cycle, with the use of a Kaggle binary classification data set and taking to explore various techniques from pre-processing to the final optimization and model evaluation, also we highlight on the data imbalance issue and we discuss the different methods of handling that imbalance on the data level by over-sampling and under sampling not only to reach a balanced class representation but to improve the overall performance. This work also opens some gaps for future work.