Movie Recommender Systems: Concepts, Methods, Challenges, and Future Directions

Area of Science:

• Computer Science
• Artificial Intelligence
• Information Retrieval

Background:

• Movie recommender systems aim to provide personalized user suggestions based on preferences.
• Effective systems require matching movies with high similarity and performance.
• Advancements in machine learning have significantly impacted recommender system development.

Purpose of the Study:

• To conduct a systematic literature review of movie recommender systems.
• To identify and analyze filtering criteria, algorithms, performance metrics, and implementation challenges.
• To provide recommendations for future research in the field.

Main Methods:

• Systematic literature review methodology.
• Analysis of popular machine learning algorithms including K-means clustering, Principal Component Analysis (PCA), and Self-Organizing Maps with PCA.
• Emphasis on metaheuristic-based recommendation systems.

Main Results:

• Detailed discussion of various algorithms and their application in movie recommendations.
• Identification of key performance measurement criteria.
• Highlighting current challenges in implementing effective recommender systems.

Conclusions:

• The study synthesizes current advancements in movie recommender systems.
• It identifies critical areas for improvement to overcome implementation challenges.
• The findings offer valuable insights for researchers and data scientists in recommender systems.