Research Article
Multiobjective Personalized Recommendation Algorithm Using Extreme Point Guided Evolutionary Computation
Table 7
HV comparison results under different settings of K to MOEA-EPG on the accuracy-coverage space.
| | Data sets | K=0.3 | K=0.5 | K=0.7 | K=0.9 |
| | Movielens 1 | 2.861 6.05e-02 | 3.203 7.74e-02 | 3.013 1.01e-01 | 2.914 7.30e-02 | | Movielens 2 | 3.944 3.06e-02 | 4.4384.51e-01 | 3.334 4.03e-02 | 4.5922.86e-02 | | Movielens 3 | 2.597 1.35e-02 | 3.343 1.07e-01 | 2.816 8.29e-02 | 2.387 6.77e-02 | | Movielens 4 | 5.659 3.46e-02 | 5.985 5.62e-02 | 5.461 4.52e-02 | 5.700 3.12e-02 | | Netflix 1 | 2.762 8.49e-02 | 2.877 7.49e-02 | 2.425 3.27e-02 | 1.961 1.28e-02 | | Netflix 2 | 7.102 5.00e-02 | 6.914 5.29e-02 | 6.434 3.58e-02 | 6.370 4.15e-02 | | Netflix 3 | 4.619 2.66e-02 | 5.082 3.62e-02 | 4.437 7.19e-02 | 3.696 3.55e-02 | | Netflix 4 | 1.791 4.82e-02 | 1.975 1.05e-02 | 1.594 1.45e-02 | 1.239 5.07e-02 |
|
|
