Network-Based Transfer Learning Helps Improve Short-Term Crime Prediction Accuracy

• URL: http://arxiv.org/abs/2406.06645v2
• Date: Thu, 13 Jun 2024 18:02:17 GMT
• Title: Network-Based Transfer Learning Helps Improve Short-Term Crime Prediction Accuracy
• Authors: Jiahui Wu, Vanessa Frias-Martinez,
• Abstract summary: We propose a novel transfer learning framework for short-term crime prediction models. Our results show that the proposed framework improves the F1 scores for target cities with mobility data scarcity. We also show that the F1 score improvements are pervasive across different types of crimes and diverse cities in the US.
• Score: 1.1062397685574308
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning architectures enhanced with human mobility data have been shown to improve the accuracy of short-term crime prediction models trained with historical crime data. However, human mobility data may be scarce in some regions, negatively impacting the correct training of these models. To address this issue, we propose a novel transfer learning framework for short-term crime prediction models, whereby weights from the deep learning crime prediction models trained in source regions with plenty of mobility data are transferred to target regions to fine-tune their local crime prediction models and improve crime prediction accuracy. Our results show that the proposed transfer learning framework improves the F1 scores for target cities with mobility data scarcity, especially when the number of months of available mobility data is small. We also show that the F1 score improvements are pervasive across different types of crimes and diverse cities in the US.

Related papers

• Incorporating Long-term Data in Training Short-term Traffic Prediction Model [6.392992843318724]
  Two datasets containing taxi and bike usage spanning over eight years in New York were used to test such effects. Experiments were conducted to assess the precision of models trained with data in the most recent 12, 24, 48, and 96 months. It was found that the training set encompassing 96 months, at times, resulted in diminished accuracy, which might be owing to disparities between historical traffic patterns and present ones.
  arXiv  Detail & Related papers  (2024-10-16T01:22:01Z)
• Demo2Vec: Learning Region Embedding with Demographic Information [0.23020018305241333]
  We show how the simple and easy-to-access demographic data can improve the quality of state-of-the-art region embedding. We find that existing pre-train methods based on KL divergence are potentially biased towards mobility information. Experimental results from both New York and Chicago show that mobility + income is the best pre-train data combination.
  arXiv  Detail & Related papers  (2024-09-25T11:39:16Z)
• STDA-Meta: A Meta-Learning Framework for Few-Shot Traffic Prediction [5.502177196766933]
  We propose a novel-temporal domain adaptation (STDA) method that learns transferable meta-knowledge from data-sufficient cities in an adversarial manner. This learned meta-knowledge can improve prediction performance of data-scarce cities. Specifically, we train the STDA model using a Model-Atemporal Meta-Learning (MAML) based episode learning process.
  arXiv  Detail & Related papers  (2023-10-31T06:52:56Z)
• Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks [51.51023951695014]
  Existing model stealing defenses add deceptive perturbations to the victim's posterior probabilities to mislead the attackers. This paper proposes Isolation and Induction (InI), a novel and effective training framework for model stealing defenses. In contrast to adding perturbations over model predictions that harm the benign accuracy, we train models to produce uninformative outputs against stealing queries.
  arXiv  Detail & Related papers  (2023-08-02T05:54:01Z)
• Meta-Learning over Time for Destination Prediction Tasks [53.12827614887103]
  A need to understand and predict vehicles' behavior underlies both public and private goals in the transportation domain. Recent studies have found, at best, only marginal improvements in predictive performance from incorporating temporal information. We propose an approach based on hypernetworks, in which a neural network learns to change its own weights in response to an input.
  arXiv  Detail & Related papers  (2022-06-29T17:58:12Z)
• Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Prediction [60.508960752148454]
  This work proposes a Spatial-Temporal Hypergraph Self-Supervised Learning framework to tackle the label scarcity issue in crime prediction. We propose the cross-region hypergraph structure learning to encode region-wise crime dependency under the entire urban space. We also design the dual-stage self-supervised learning paradigm, to not only jointly capture local- and global-level spatial-temporal crime patterns, but also supplement the sparse crime representation by augmenting region self-discrimination.
  arXiv  Detail & Related papers  (2022-04-18T23:46:01Z)
• A model for traffic incident prediction using emergency braking data [77.34726150561087]
  We address the fundamental problem of data scarcity in road traffic accident prediction by training our model on emergency braking events instead of accidents. We present a prototype implementing a traffic incident prediction model for Germany based on emergency braking data from Mercedes-Benz vehicles.
  arXiv  Detail & Related papers  (2021-02-12T18:17:12Z)
• The effect of differential victim crime reporting on predictive policing systems [84.86615754515252]
  We show how differential victim crime reporting rates can lead to outcome disparities in common crime hot spot prediction models. Our results suggest that differential crime reporting rates can lead to a displacement of predicted hotspots from high crime but low reporting areas to high or medium crime and high reporting areas.
  arXiv  Detail & Related papers  (2021-01-30T01:57:22Z)
• Leveraging Mobility Flows from Location Technology Platforms to Test Crime Pattern Theory in Large Cities [26.100870516361347]
  We study the ability of granular human mobility in describing and predicting crime concentrations at an hourly scale. Our evaluation infers mobility flows by leveraging an anonymized dataset from Foursquare that includes almost 14.8 million consecutive check-ins in three major U.S. cities.
  arXiv  Detail & Related papers  (2020-04-17T14:21:10Z)
• Exploring Spatio-Temporal and Cross-Type Correlations for Crime Prediction [48.1813701535167]
  We perform crime prediction exploiting the cross-type and-temporal correlations of urban crimes. We propose a coherent framework to mathematically model these correlations for crime prediction. Further experiments have been conducted to understand the importance of different correlations in crime prediction.
  arXiv  Detail & Related papers  (2020-01-20T00:34:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.