Accès libre

Research on performance improvement of personalized recommendation algorithm based on deep neural network optimization

Xianglin Xiao

Xianglin Xiao

Department of Information Engineering, Sichuan Vocational and Technical College of CommunicationChengdu, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Xiao, Xianglin
  
21 mars 2025
Research on performance improvement of personalized recommendation algorithm based on deep neural network optimization's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 21 mars 2025
Reçu: 29 oct. 2024
Accepté: 06 févr. 2025
DOI: https://doi.org/10.2478/amns-2025-0623
Mots clés
© 2025 Xianglin Xiao, published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Recommendation accuracy
Recommendation accuracy

Figure 2.

The influence of output dimension
The influence of output dimension

Figure 3.

The influence of activation function
The influence of activation function

Figure 4.

The impact of potential dimensions on the recommendation effect
The impact of potential dimensions on the recommendation effect

Figure 5.

Performance of the model
Performance of the model

Figure 6.

The variation trend of HR and NDCG
The variation trend of HR and NDCG

Dataset

Dataset Number of interactions Number of users Number of projects Sparsity
Movie Lens 1000309 3807 6050 95.42%
Pinterest 1500709 9948 55175 99.68%

HR values of different MLP layers

Dataset Factors MLP-0 MLP-1 MLP-2 MLP-4
MovieLens 8 0.46 0.629 0.668 0.665
16 0.45 0.678 0.685 0.69
32 0.464 0.693 0.702 0.709
Pinterest 8 0.298 0.85 0.853 0.862
16 0.301 0.867 0.856 0.862
32 0.298 0.87 0.861 0.86

Model pretraining

Training Factors MovieLens Pinterest
HR NDCG HR NDCG
With Pre_training 8 0.707 0.402 0.885 0.564
16 0.722 0.445 0.88 0.567
32 0.721 0.446 0.891 0.548
Without Pre_training 8 0.679 0.409 0.879 0.545
16 0.704 0.421 0.875 0.559
32 0.71 0.442 0.868 0.545
Langue:
Anglais
Périodicité:
1 fois par an
Sujets de la revue:
Sciences de la vie, Sciences de la vie, autres, Mathématiques, Mathématiques appliquées, Mathématiques générales, Physique, Physique, autres
RSS Feed de la revue