Summary of Contextual Data Integration For Bike-sharing Demand Prediction with Graph Neural Networks in Degraded Weather Conditions, by Romain Rochas (licit-eco7 et al.
Contextual Data Integration for Bike-sharing Demand Prediction with Graph Neural Networks in Degraded Weather Conditions
by Romain Rochas, Angelo Furno, Nour-Eddin El Faouzi
First submitted to arxiv on: 4 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- 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 study investigates how various factors, such as weather, events, and transportation mode availability, impact bike-sharing demand. The authors analyze the effectiveness of incorporating contextual data, including weather, time embedding, and road traffic flow, to predict bike-sharing Origin-Destination (OD) flows in atypical weather situations. The results show a mild relationship between prediction quality and road traffic flow, with introduced time embedding allowing for improved performance compared to state-of-the-art methods. Additionally, the inclusion of weather data as an additional input further reduces the prediction error by over 20% in degraded weather conditions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A group of researchers looked at why people are more likely to use bike-sharing services on certain days and in different weather conditions. They wanted to know which factors make a difference. They found that knowing how traffic is moving can help them predict when people will be using bike-sharing services, especially on rainy or snowy days. By adding extra information about the weather and time of day, they were able to improve their predictions even more. |
Keywords
» Artificial intelligence » Embedding
