The Effects of Data Sampling with Deep Learning and Highly Imbalanced Big Data

摘要

Training predictive models with class-imbalanced data has proven to be a difficult task. This problem is well studied, but the era of big data is producing more extreme levels of imbalance that are increasingly difficult to model. We use three data sets of varying complexity to evaluate data sampling strategies for treating high class imbalance with deep neural networks and big data. Sampling rates are varied to create training distributions with positive class sizes from 0.025%-90%. The area under the receiver operating characteristics curve is used to compare performance, and thresholding is used to maximize class performance. Random over-sampling (ROS) consistently outperforms under-sampling (RUS) and baseline methods. The majority class proves susceptible to misrepresentation when using RUS, and results suggest that each data set is uniquely sensitive to imbalance and sample size. The hybrid ROS-RUS maximizes performance and efficiency, and is our preferred method for treating high imbalance within big data problems.