Real-Time Abnormal Address Detection for Mobile Devices in Location-Based Services

An address, a textual description of a geographical location, plays an important role in location-based services such as instant delivery. However, abnormal addresses (i.e., an address without detailed or accurate information) have led to significant costs. In real-world settings, abnormal address detection is not trivial because it needs to be completed in real-time to support massive online queries from mobile devices. In this study, we design <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FastAddr</monospace>, a fast abnormal address detection framework, which detects abnormal addresses in real time. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FastAddr</monospace> consists of a novel contrastive address augmentation module and a lightweight multi-head attention model. We further design <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FastAddr</monospace>+ to enhance <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FastAddr</monospace> by utilizing large-scale spatial entities. A comprehensive three-phase evaluation is conducted. (i) We evaluate <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FastAddr</monospace> on a real-world dataset and it yields the average F1 of 85.7% in 0.058 milliseconds, which outperforms the state-of-the-art models by 47.4% with a similar detection time. (ii) An offline A/B test shows that <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FastAddr</monospace> outperforms the previous model significantly. (iii) We also conduct an online A/B test to compare <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FastAddr</monospace> with the deployed model, which shows an improvement of F1 by more than 20%. Moreover, we conduct two case studies on real industry data, demonstrating both the efficiency and effectiveness of <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FastAddr</monospace>.