A Survey of Predictive Modelling under Imbalanced Distributions

Abstract

Many real world data mining applications involve obtaining predictive models using data sets 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 modelling techniques. This paper 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 distributions, describe the main approaches to these problems, propose a taxonomy of these methods and refer to some related problems within predictive modelling.

References in corpus (4)

• SMOTE: Synthetic Minority Over-sampling Technique
• Learning When Training Data are Costly: The Effect of Class Distribution on Tree Induction
• A graphical analysis of cost-sensitive regression problems
• Soft (Gaussian CDE) regression models and loss functions

Cited by in corpus (6)

• Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G
• UBL: an R package for Utility-based Learning
• Surprise sampling: improving and extending the local case-control sampling
• Unsupervised Contextual Anomaly Detection using Joint Deep Variational Generative Models
• Predictive Modeling of Hospital Readmission: Challenges and Solutions
• As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning