Hybrid recommendation system combined content-based filtering and collaborative prediction using artificial neural network
Introduction
Nowadays, with the ever increasing volume, complexity and availability of online information, recommendation systems have been an effective solution to overcome such information overload [1][2].
The main objective of a recommender system is to predict user preferences, in another way system that offer specific items to users among a large number of choices according to their tastes. Suggestions for movies on Netflix, or products on Amazon, or Videos on YouTube, are real-world examples of using recommender systems in our life [3].
In the mid-1990s, recommendation systems became a famous topic of research. Awareness in recommendation systems has grown significantly in recent years, and recommendation systems now play a significant role in commercial websites and well-known businesses such as Spotify, Facebook, LinkedIn, and IMdb because these systems help them to increase the number of items sold and sell more diversified items or even increase the user satisfaction. This demand for this type of systems has given the green light to researchers to develop powerful systems and several researches have been carried out in this field [4].
A recommendation method must demonstrate that a product needs to be recommended in order to find relevant products for the user. There are many kinds of recommendation algorithm approaches for this, the most prominent of which are collaborative filtering, content-based filtering, and hybrid systems.
Recommendations to the active client in the Collaborative Filtering approach are focused on items/products that other users with common preferences have enjoyed in the past. Many users’ taste similarity is determined based on the similarity of ranking data (scale of 1 to 5 for movies) or the users’ browsing history. The Content-Based model suggests products to the active user based on items he has already enjoyed. The resemblance of the products is determined by the characteristics associated with the compared items, such as the context, title, or even the product picture. For example, if a user gives a song in the HipHop genre a favorable rating, the machine can learn to recommend other songs in that genre. Hybrid methods [5][6] are built on combining existing strategies to benefit from the advantages of both and the fewest disadvantages. The most well-known and widely used solution is to incorporate Collaborative Filtering with other approaches [7].
We previously suggested a novel intelligent recommendation system [8] that integrates collaborative filtering and K-means clustering in our earlier work. Also, when items (movies) are grouped by genre attributes using K-means and users are categorized based on their item preferences and the genres they prefer to watch, we employed specific user demographic attributes such as gender and age to construct segmented user profiles [9]. Then The Collaborative Filtering technique is used to the cluster where the user belongs to recommend items to an active user.
In this paper, we propose a powerful recommendation method based on a Hybrid approach that blends Collaborative Filtering with Content-Based and is supervised by the ranking list provided by the self-organizing map, a well-known unsupervised learning artificial neural network technique.
The following is a summary of the paper’s structure. The following section discusses related work in the recommendation area. The adaptive solution and the various steps to construct our system are presented in Section 2. Sections 3 Proposed work, 4 Result and discussion describe the methods used to compare our system to other state-of-the-art approaches in the field of recommendation and analyze the results.
Section snippets
Related work
Several research efforts have been made to combine different recommendation approaches. Andreu Vall et al. [5] offers a hybrid recommender system combining two feature combination (profiles and membership) for the automated continuation of music playlists, they proposed a system that extends collaborative filtering by considering not only playlists organized by hand, but also by incorporating any type of song functionality vector. To boost prediction accuracy, R. Logesh et al. [10] suggest a
Proposed work
Famous movie companies such as IMDB and Netflix have conducted extensive studies into the use of recommendation services in the film industry, taking into account both content and customer details in their recommendations. This section proposes a modern hybrid recommendation model with four key components: collaborative filtering, content-based filtering, SOM collaborative filtering and Hybrid filtering.
The dataset
To evaluate our system, we use the Movielens100k dataset because it is publicly available and widely used in the evaluation of recommendation models.
The dataset contain 100.000 rating divided into 90570 rating for the train set and 9430 for the test set, the ratings are values from 1 to 5 scale, 1 mean movies negatively rated and 5 movies positively rated, all ratings exist in our dataset are distributed as shown in Fig. 3.
All ratings are given by 943 users on 1682 movies, the selected users
Conclusion and future work
In this paper, we propose a new hybrid model of a movie recommendation framework based on three models: collaborative filtering, content-based, and CF with a self-organizing map model that takes the age demographic attribute into account. The main advantages of our system is to combine all the scores of all models and benefit from the advantages of each of them. Even our system takes a lot of recommendation time speed compared to the other models but the precision and the performance
References (21)
- et al.
Intelligent recommender system based on unsupervised machine learning and demographic attributes
Simul. Model. Pract. Theory
(2021) - et al.
Providing effective recommendations in discussion groups using a new hybrid recommender system based on implicit ratings and semantic similarity
Electron. Commer. Res. Appl.
(2020) - et al.
DST-HRS: A topic driven hybrid recommender system based on deep semantics
Comput. Commun.
(2020) - et al.
A content-based recommender system for computer science publications
Knowl.-Based Syst.
(2018) - et al.
A novel approach based on heuristics and a neural network to solve a capacitated location routing problem
Simul. Model. Pract. Theory
(2020) - et al.
Evaluation of recommender systems: A new approach
Expert Syst. Appl.
(2008) - et al.
The MovieLens datasets: History and context
ACM Trans. Interact. Intell. Syst.
(2016) - et al.
A self-organizing map based knowledge discovery for music recommendation systems
- et al.
A hybrid recommender system combining collaborative filtering with neural network
- et al.
An enhanced CBAR algorithm for improving recommendation systems accuracy
Simul. Model. Pract. Theory
(2016)
Cited by (66)
Interpretable hierarchical error correction GRU model for effective observation selection
2023, Applied Soft ComputingLEARNING OBJECT FROM EMERGENCE TO NOWADAYS: SYSTEMATICS LITERATURE REVIEW
2024, Journal of Theoretical and Applied Information TechnologyNew Custom Rating for Improving Recommendation System Performance
2024, Research SquareA hybrid collaborative filtering mechanism for product recommendation system
2024, Multimedia Tools and ApplicationsMCARS-CC: A Salable Multicontext-Aware Recommender System
2024, IEEE Transactions on Computational Social Systems