Electricity Theft Detection with self-attention

TL;DR

This paper introduces a novel self-attention based model with dilated convolutions and a binary mask for electricity theft detection, significantly improving accuracy on real-world imbalanced data.

Contribution

The work presents a new self-attention model with dilated convolutions and a binary mask for handling missing data in electricity theft detection.

Findings

Achieved an AUC of 0.926, over 17% better than previous methods.

Effectively handled missing data with the binary mask.

Demonstrated improved detection performance on real-world dataset.

Abstract

In this work we propose a novel self-attention mechanism model to address electricity theft detection on an imbalanced realistic dataset that presents a daily electricity consumption provided by State Grid Corporation of China. Our key contribution is the introduction of a multi-head self-attention mechanism concatenated with dilated convolutions and unified by a convolution of kernel size $1$. Moreover, we introduce a binary input channel (Binary Mask) to identify the position of the missing values, allowing the network to learn how to deal with these values. Our model achieves an AUC of $0.926$ which is an improvement in more than $17\%$ with respect to previous baseline work. The code is available on GitHub at https://github.com/neuralmind-ai/electricity-theft-detection-with-self-attention.