Summary of Incorporating Long-term Data in Training Short-term Traffic Prediction Model, by Xiannan Huang et al.
Incorporating Long-term Data in Training Short-term Traffic Prediction Model
by Xiannan Huang, Shuhan Qiu, Yan Cheng, Quan Yuan, Chao Yang
First submitted to arxiv on: 16 Oct 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 approach investigates the effect of augmented datasets on short-term traffic volume predictions. By utilizing two extensive datasets spanning eight years in New York, researchers examined the impact of training sets containing 12, 24, 48, and 96 months’ worth of data. Surprisingly, models trained with 96-month datasets sometimes exhibited diminished accuracy due to historical pattern disparities. To address these shifts, a novel approach was developed, combining a covariate distribution alignment scheme with an environment-aware learning method. Experimental results on real-world datasets demonstrated the effectiveness of this method in reducing testing errors and improving accuracy when training with large-scale historical data. This work is the first to assess the impact of expanding training datasets on traffic prediction model accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers studied how big datasets can help predict traffic volumes. They used two big datasets from New York that had information from eight years ago. They tested different models using data from one year, two years, four years, and eight years ago. Surprisingly, the model that used data from eight years ago didn’t always work better – sometimes it even got worse! This might be because traffic patterns changed over time. The researchers came up with a new way to train models that can handle these changes and make them more accurate when using big datasets. |
Keywords
» Artificial intelligence » Alignment
