Research Reports

Permanent URI for this collectionhttp://dl.cerist.dz/handle/CERIST/34

Browse

Start date: 2024Subject: search.filters.subject.Cloud service

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Two-tower neural network for personalizing service recommendation in cloud environment
    (CERIST, 2025-02) Lebib, Fatma Zohra; Meziane, Abdelkrim
    Effective cloud service recommendation necessitates a deep understanding of both user preferences and the diversity of cloud services. This paper proposes a novel two-tower neural network architecture to address this challenge. By leveraging the power of neural networks, we create concise representations of users and cloud services, enabling highly personalized recommendations. Our two-tower architecture is designed to efficiently scale to the massive scale of cloud environments. Each tower, dedicated to users and cloud services respectively, integrates relevant features and interaction data to generate dense embeddings. Cloud services are then ranked based on their similarity to the user’s embedding, ensuring accurate and tailored suggestions. The proposed two-tower model was evaluated on the WSdream dataset for both regression and classification tasks. Experimental results consistently demonstrated superior performance compared to state-of-the-art recommendation techniques, including k-nearest neighbors and matrix factorization.
  • Thumbnail Image
    Item
    Matrix Factorization for cloud service recommendation based on social trust
    (CERIST, 2024-04) Lebbib, Fatma Zohra; Djebrit, Ichrak; Mahmoudi, Khadidja
    Recommending trustworthy cloud services is essential to establishing credibility and ensuring better user decision-making based on their specific needs. Traditional recommendation approaches based on collaborative filtering face some challenges, including data sparsity issues. In this paper, a social trust-based recommendation approach using matrix factorization is proposed to improve recommendation accuracy and address the limitations imposed by data sparsity in recommender systems. First, the level of trustworthiness of users is inferred from their interactions on social networks. Then, the social trust model is integrated with the matrix factorization technique to generate reliable recommendations for users. The results of experiments conducted on the Epinions and WSdream datasets demonstrate that social trust significantly improves recommendation accuracy compared to state-of-the-art recommendation systems that do not take trust into account.