Research and Application of User Behavior Data Analysis Technology for E-commerce
, et
27 févr. 2025
À propos de cet article
Publié en ligne: 27 févr. 2025
Reçu: 25 sept. 2024
Accepté: 23 janv. 2025
DOI: https://doi.org/10.2478/amns-2025-0116
Mots clés
© 2025 Xiaohan Yuan et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.
Figure 1.
Figure 2.
Figure 3.
Figure 4.
Figure 5.
Figure 6.
Figure 7.
Figure 8.
Figure 9.
Figure 10.
Comparison of effects of three models
| Model Name | Accuracy rate | Recall rate | F1 Value |
|---|---|---|---|
| Logistic regression | 4.25% | 4.31% | 4.27% |
| LightGBM | 5.61% | 5.63% | 5.62% |
| LightGBM + LR | 5.81% | 602.70% | 5.93% |
Evaluation indicators of each algorithm
| Precision | Coverage | MAE | Diversity | Surprise | Unexpectedness | |
|---|---|---|---|---|---|---|
| 16.68% | 8.34% | 89.11% | 0.365 | 10.956 | 8.841 | |
| 23.94% | 99.20% | 78.68% | 0.914 | 8.130 | 1.633 | |
| 26.40% | 99.20% | 76.93% | 0.936 | 8.242 | 1.444 |
Overall prediction results
| Model Name | Accuracy rate | Recall rate | F1 |
|---|---|---|---|
| Logistic regression | 4.66% | 4.72% | 4.68% |