Research Article
[Retracted] Research on Data Mining Algorithm of Associated User Network Based on Multi-Information Fusion
| | Recommendations based on demographics | Content-based recommendations | Recommendations based on collaborative filtering |
| Advantages | Easy to implement Depend on less No cold start problem | Grasp users’ taste accurately | Low modeling requirements No machine understanding required High openness, good reference | Disadvantages | Accuracy is poor Ignoring users’ tastes Sensitive information is difficult to obtain | Accuracy depends on modeling comprehensiveness Ignore the user’s attitude towards the object cold start problem exists | Sparse matrix affects accuracy Cold start problem It is hard to update in real time |
|
|