Table 9 Average relative change in F1 score using M for property crimes over all test months (Aug-Dec) in each city
From: Enhancing short-term crime prediction with human mobility flows and deep learning architectures
Model | Bal | Min | Aus | Chi |
|---|---|---|---|---|
HALR | 3.7% | 0.2% | −2.9% | −2.3% |
GRU | 1.9% | 2.4% | −1.6% | 0.3% |
Attn | 4.6% | 1.7% | −2.9% | 0.4% |
GCN | −2.8% | −1.7% | −1.5% | −2.0% |
GGConv | 4.2% | 1.8% | 0.9% | 0.4% |
NbConv | 6.0% | 2.8% | 1.4% | 3.3% |