An Approach for Multi-Context-Aware Multi-Criteria Recommender Systems Based on Deep Learning

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 99936 - 99948

Published: Jan. 1, 2024

In an era where digital information is abundant, the role of recommender systems in navigating this vast landscape has become increasingly vital. This study proposes a novel deep learning-based approach integrating multi-context and multi-criteria data within unified neural network framework. The model processes these dimensions concurrently, significantly improving precision personalized recommendations. Context-aware extend traditional two-dimensional user-item preference methods with context awareness multiple criteria. contrast to methods, our intricately weaves together its architecture. concurrent processing enables sophisticated interactions between criteria, enhancing recommendation accuracy. While context-aware incorporate contextual such as time location when making recommendations, multi-criteria-based approaches offer spectrum evaluative enriching user experience more tailored relevant suggestions. Although both have advantages producing accurate referrals, ratings not been employed for Our research multi-context, system address gap. that process separately, learning integration staged; are concurrently processed through facilitates interaction criteria by embedding elements into core network's layers. methodology enhances system's adaptability improves delivering leveraging compounded effects criteria-specific insights. proposed shows superior performance predictive tasks, achieving lowest Mean Absolute Error (MAE) Root Square (RMSE) on TripAdvisor ITMRec datasets compared other state-of-the-art techniques. demonstrate robustness accuracy model.

Language: Английский

---

UBAR: User Behavior-Aware Recommendation with knowledge graph

Knowledge-Based Systems, Journal Year: 2022, Volume and Issue: 254, P. 109661 - 109661

Published: Aug. 12, 2022

Language: Английский

---

AI-Enabled Trust in Distributed Networks

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 88116 - 88134

Published: Jan. 1, 2023

Cybersecurity, as a crucial aspect of the information society, requires significant attention. Fortunately, concept trust, rooted in sociology, has been studied order to enhance cybersecurity by evaluating trustworthiness nodes with artificial intelligence (AI) techniques distributed networks (DNs). However, scalability issues faced AI-enabled trust hinder its integration DNs. Currently, there is lack comprehensive review article that explores current state development applications. This paper aims address this gap providing state-of-the-art focuses on and how it can be facilitated through AI, particularly utilizing machine learning deep methods. Additionally, provides comparison analysis three key domains field trust: management (TM), intrusion detection systems (IDS), recommender (RS). Some open problems challenges currently exist are manifested, some suggestions for future work presented.

Language: Английский

---

DHSIRS: a novel deep hybrid side information-based recommender system

Multimedia Tools and Applications, Journal Year: 2023, Volume and Issue: 82(22), P. 34513 - 34539

Published: March 7, 2023

Language: Английский

---

Research on Deep Learning-Based Algorithm and Model for Personalized Recommendation of Resources

Journal of Applied Data Sciences, Journal Year: 2023, Volume and Issue: 4(2), P. 68 - 75

Published: May 1, 2023

Resource recommendation system is a new type of management system, which uses personalized information to solve business needs such as customer consultation and product recommendation, provides users with high quality services achieves accurate marketing, so nowadays resource has pivotal role in modern management. In this paper, I study the algorithm model based on deep learning, taking human an example.

Language: Английский

---

Addressing sparse data challenges in recommendation systems: A Systematic review of rating estimation using sparse rating data and profile enrichment techniques

Intelligent Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 200474 - 200474

Published: Jan. 1, 2025

Language: Английский

---

A healthy and reliable rating profile expansion approach to address data sparsity in food recommendation systems

Knowledge and Information Systems, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 20, 2025

Language: Английский

---

Influencer Ranking Framework Using TH-DCNN for influence maximization

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 252, P. 583 - 592

Published: Jan. 1, 2025

Language: Английский

---

A personalized reinforcement learning recommendation algorithm using bi-clustering techniques

PLoS ONE, Journal Year: 2025, Volume and Issue: 20(2), P. e0315533 - e0315533

Published: Feb. 20, 2025

Recommender systems have become a core component of various online platforms, helping users get relevant information from the abundant digital data. Traditional RSs often generate static recommendations, which may not adapt well to changing user preferences. To address this problem, we propose novel reinforcement learning (RL) recommendation algorithm that can give personalized recommendations by adapting However, significant drawback RL-based is they are computationally expensive. Moreover, these fail extract local patterns residing within dataset result in generation low quality recommendations. The proposed work utilizes biclustering technique create an efficient environment for RL agents, thus, reducing computation cost and enabling dynamic Additionally, used find locally associated dataset, further improves efficiency agent’s process. experiments eight state-of-the-art algorithms identify appropriate given task. This innovative integration addresses key gaps existing literature. introduced strategy predict item ratings framework. validity evaluated on three datasets movies domain, namely, ML100K, ML-latest-small FilmTrust. These diverse were chosen ensure reliable examination across scenarios. As per nature RL, some specific evaluation metrics like personalization, diversity, intra-list similarity novelty measure diversity investigation motivated need recommender dynamically adjust changes customer Results show our showed promising results when compared with techniques.

Language: Английский

---

Understanding customer loyalty-aware recommender systems in E-commerce: an analytical perspective

Electronic Commerce Research, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 20, 2025

Language: Английский

---