Summary of Network-based Transfer Learning Helps Improve Short-term Crime Prediction Accuracy, by Jiahui Wu and Vanessa Frias-martinez
Network-Based Transfer Learning Helps Improve Short-Term Crime Prediction Accuracy
by Jiahui Wu, Vanessa Frias-Martinez
First submitted to arxiv on: 10 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computers and Society (cs.CY)
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 This novel transfer learning framework enhances short-term crime prediction models by leveraging human mobility data from source regions with abundant mobility information to fine-tune local crime prediction models in target regions. By transferring weights from deep learning architectures trained on historical crime data, this approach improves accuracy in regions where mobility data is scarce. The results demonstrate F1 score improvements for target cities with limited mobility data, across various types of crimes and US cities. This framework’s ability to adapt to diverse cities and crime types underscores its potential for real-world applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper helps predict where crimes will happen soon. They used special computer models that learn from past crimes, but these models need data about how people move around a city. In some places, this data is hard to get, which makes the models less accurate. To solve this problem, they came up with a new way to use the model from one place and adapt it for another. This helps make predictions better in cities where we don’t have much mobility data. |
Keywords
» Artificial intelligence » Deep learning » F1 score » Transfer learning
