Hybrid and Ensemble-Based Personalized Recommender System - Solving Data Sparsity Problem
| Autor: | Taehyung Wang, Akshay Shukla, Lousia Manoael |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
User profile
business.industry Computer science media_common.quotation_subject Entertainment industry Recommender system Machine learning computer.software_genre Prime (order theory) Product (business) Consistency (database systems) Collaborative filtering Quality (business) Artificial intelligence business computer media_common |
| Zdroj: | 2021 Third International Conference on Transdisciplinary AI (TransAI). |
| DOI: | 10.1109/transai51903.2021.00029 |
| Popis: | Online content streaming is the most popular form of entertainment in recent times due to COVID 19 lockdown. All popular streaming services use various product recommendation schemes to retain users to their services by intriguing them with content that they might like. Various recommendation systems have been used by famous streaming services like Netflix, Amazon Prime, Hulu, etc. but they lack consistency and accuracy as they suffer from some severe problems such as the first rater problem, sparsity problem, and various computations problems. In this research, we have come up with a hybrid machine learning recommender system which uses an ensemble of content-based and collaborative filtering techniques to not only solve all data sparsity problems but also provide more personalized recommendations to the users based on their watching history and user profile. This research provides a new algorithm that increases the quality of content that is being recommended to the users. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|