On the Reduction of Biases in Big Data Sets for the Detection of Irregular Power Usage
This work addresses biased data sets in the domain of irregular power usage detection, particularly in emerging markets where electricity theft can reach up to 40%, but it is incremental as it applies a novel framework to a specific application.
The paper tackles the problem of biases like class imbalance and covariate shift in high-dimensional data sets for detecting irregular power usage, showing that reducing these biases increases predictor accuracy, with potential economic value as the models are deployed in commercial software.
In machine learning, a bias occurs whenever training sets are not representative for the test data, which results in unreliable models. The most common biases in data are arguably class imbalance and covariate shift. In this work, we aim to shed light on this topic in order to increase the overall attention to this issue in the field of machine learning. We propose a scalable novel framework for reducing multiple biases in high-dimensional data sets in order to train more reliable predictors. We apply our methodology to the detection of irregular power usage from real, noisy industrial data. In emerging markets, irregular power usage, and electricity theft in particular, may range up to 40% of the total electricity distributed. Biased data sets are of particular issue in this domain. We show that reducing these biases increases the accuracy of the trained predictors. Our models have the potential to generate significant economic value in a real world application, as they are being deployed in a commercial software for the detection of irregular power usage.