Summary of Sttm: a New Approach Based Spatial-temporal Transformer and Memory Network For Real-time Pressure Signal in On-demand Food Delivery, by Jiang Wang et al.
STTM: A New Approach Based Spatial-Temporal Transformer And Memory Network For Real-time Pressure Signal In On-demand Food Delivery
by Jiang Wang, Haibin Wei, Xiaowei Xu, Jiacheng Shi, Jian Nie, Longzhi Du, Taixu Jiang
First submitted to arxiv on: 29 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Spatio-Temporal Transformer and Memory Network (STTM) method is designed to predict Real-time Pressure Signals (RPS) in On-demand Food Delivery (OFD) services. The RPS measures the pressure on the logistics system, which affects the delivery time of orders. Previous methods like DeepFM, RNN, and GNN are limited by their inability to utilize unique temporal and spatial characteristics of OFD services, particularly during sudden severe weather conditions or peak periods. STTM addresses these issues by incorporating a novel Spatio-Temporal Transformer structure that learns logistics features across temporal and spatial dimensions, as well as encoding historical information of business districts and their neighbors. Additionally, a Memory Network is employed to increase sensitivity to abnormal events. Experimental results show that STTM outperforms previous methods in both offline experiments and online A/B tests. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new method called Spatio-Temporal Transformer and Memory Network (STTM) to predict Real-time Pressure Signals (RPS) in On-demand Food Delivery (OFD) services. RPS measures the pressure on the logistics system, which affects delivery times. The current method doesn’t work well during severe weather or peak periods. STTM uses a special structure that learns about time and space, as well as remembering past events to be more accurate. |
Keywords
» Artificial intelligence » Gnn » Rnn » Transformer
