A survey on addressing high-class imbalance in big data

TLDR

Class imbalance in majority–minority classification can bias classifiers toward the majority class, and in big data with extreme ratios (100:1–10,000:1) this bias can have costly adverse effects. This survey reviews studies from the past eight years on high-class imbalance (100:1–10,000:1) in big data to evaluate current mitigation approaches. The review examines data-level sampling methods and algorithm-level cost-sensitive and hybrid/ensemble techniques. The authors find that data sampling—especially Random Over-Sampling—generally outperforms other methods, while algorithm-level approaches show promising but inconsistent results, highlighting a need for more comprehensive comparative studies.

Abstract

In a majority–minority classification problem, class imbalance in the dataset(s) can dramatically skew the performance of classifiers, introducing a prediction bias for the majority class. Assuming the positive (minority) class is the group of interest and the given application domain dictates that a false negative is much costlier than a false positive, a negative (majority) class prediction bias could have adverse consequences. With big data, the mitigation of class imbalance poses an even greater challenge because of the varied and complex structure of the relatively much larger datasets. This paper provides a large survey of published studies within the last 8 years, focusing on high-class imbalance (i.e., a majority-to-minority class ratio between 100:1 and 10,000:1) in big data in order to assess the state-of-the-art in addressing adverse effects due to class imbalance. In this paper, two techniques are covered which include Data-Level (e.g., data sampling) and Algorithm-Level (e.g., cost-sensitive and hybrid/ensemble) Methods. Data sampling methods are popular in addressing class imbalance, with Random Over-Sampling methods generally showing better overall results. At the Algorithm-Level, there are some outstanding performers. Yet, in the published studies, there are inconsistent and conflicting results, coupled with a limited scope in evaluated techniques, indicating the need for more comprehensive, comparative studies.