scholarly journals Movie genome: alleviating new item cold start in movie recommendation

2019 ◽  
Vol 29 (2) ◽  
pp. 291-343 ◽  
Author(s):  
Yashar Deldjoo ◽  
Maurizio Ferrari Dacrema ◽  
Mihai Gabriel Constantin ◽  
Hamid Eghbal-zadeh ◽  
Stefano Cereda ◽  
...  
Keyword(s):  
Cold Start ◽  
Movie Recommendation ◽  
New Item

scholarly journals Pairwise Preference Regression on Movie Recommendation System

2019 ◽  
Vol 4 (1) ◽  
pp. 57
Author(s):  
Rita Rismala ◽  
Rudy Prabowo ◽  
Agung Toto Wibowo
Keyword(s):  
Standard Deviation ◽  
Recommendation System ◽  
Cold Start ◽  
Pairwise Preference ◽  
Movie Recommendation ◽  
New Item ◽  
Cold Start Problem

Recommendation System is able to help users to choose items, including movies, that match their interests. One of the problems faced by recommendation system is cold-start problem. Cold start problem can be categorized into three types, they are: recommending existed item for new user, recommending new item for existed user, and recommending new item for new user. Pairwise preference regression is a method that directly deals with cold-start problem. This method can suggest a recommendation, not only for users who have no historical rating, but also for those who only have less demographic info. From the experiment result, the best score of Normalized Discounted Cumulative Gain (nDGC) from the system is 0.8484. The standard deviation of rating resulted by the recommendation system is 1.24, the average is 3.82. Consequently, the distribution of recommendation result is around rating 5 to 3. Those results mean that this recommendation system is good to solving cold-start problem in movie recommendation system.

scholarly journals MOVIE RECOMMENDATION USING KNOWLEDGE GRAPH

2020 ◽  
pp. 99-103
Author(s):  
Navin Tatyaba Gopal ◽  
Anish Raj Khobragade
Keyword(s):  
Neural Network ◽  
Recommender Systems ◽  
Weighted Graph ◽  
Cold Start ◽  
Structured Data ◽  
Label Propagation ◽  
Knowledge Graph ◽  
Movie Recommendation ◽  
Knowledge Graphs ◽  
Prior Application

The Knowledge graphs (KGs) catches structured data and relationships among a bunch of entities and items. Generally, constitute an attractive origin of information that can advance the recommender systems. But, present methodologies of this area depend on manual element thus don’t permit for start to end training. This article proposes, Knowledge Graph along with Label Smoothness (KG-LS) to offer better suggestions for the recommender Systems. Our methodology processes user-specific entities by prior application of a function capability that recognizes key KG-relationships for a specific user. In this manner, we change the KG in a specific-user weighted graph followed by application of a graph neural network to process customized entity embedding. To give better preliminary predisposition, label smoothness comes into picture, which places items in the KG which probably going to have identical user significant names/scores. Use of, label smoothness gives regularization above the edge weights thus; we demonstrate that it is comparable to a label propagation plan on the graph. Additionally building-up a productive usage that symbolizes solid adaptability concerning the size of knowledge graph. Experimentation on 4 datasets shows that our strategy beats best in class baselines. This process likewise accomplishes solid execution in cold start situations where user-entity communications remain meager.

scholarly journals Clustering Method based on Genre Interest for Cold-Start Problem in Movie Recommendation

2013 ◽  
Vol 19 (1) ◽  
pp. 57-77 ◽  
Author(s):  
Tithrottanak You ◽  
Ahmad Nurzid Rosli ◽  
Inay Ha ◽  
Geun-Sik Jo
Keyword(s):  
Cold Start ◽  
Clustering Method ◽  
Movie Recommendation ◽  
Cold Start Problem

The Comparison of Efficiency between the Recommendation Algorithm Based on Multi-Attribute Rating Matrix and the Algorithm Based on UIARM

2012 ◽  
Vol 457-458 ◽  
pp. 1544-1549
Author(s):  
Hang Yin ◽  
Gui Ran Chang ◽  
Xing Wei Wang
Keyword(s):  
Computation Time ◽  
Cold Start ◽  
Poor Quality ◽  
Recommendation Algorithm ◽  
Relevant Item ◽  
Item Attribute ◽  
Low Efficiency ◽  
Item Attributes ◽  
New Item ◽  
Cold Start Problem

this recommendation algorithm based on User-Item Attribute Rating Matrix (UIARM) can solve the cold-start problem, but the recommended low efficiency, poor quality. The use of Multi-Attribute Rating Matrix (MARM) can solve this problem; it can reduce the computation time and improve the recommendation quality effectively. The user information is analyzed to create their attribute-tables. The user's ratings are mapped to the relevant item attributes and the user's attributes respectively to generate a User Attribute-Item Attribute Rating Matrix. After UAIARM is simplified, MARM will be created. When a new item/user enters into this system, the attributes of new item/user and MARM are matched to find the N users/item with the highest match degrees as the target of the new items or the recommended items. Experiment results validate the cold-start recommendation algorithm based on MARM is efficient.

scholarly journals An enhanced framework for solving cold start problem in movie recommendation systems

2021 ◽  
Vol 24 (3) ◽  
pp. 1628
Author(s):  
Salma Adel Elzeheiry ◽  
N. E. Mekky ◽  
A. Atwan ◽  
Noha A. Hikal
Keyword(s):  
Logistic Regression ◽  
Recommendation Systems ◽  
Principal Component ◽  
Cold Start ◽  
Absolute Error ◽  
Similarity Score ◽  
Least Square ◽  
Sufficient Information ◽  
Proposed Model ◽  
Movie Recommendation

<p>Recommendation systems (RSs) are used to obtain advice regarding decision-making. RSs have the shortcoming that a system cannot draw inferences for users or items regarding which it has not yet gathered sufficient information. This issue is known as the cold start issue. Aiming to alleviate the user’s cold start issue, the proposed recommendation algorithm combined tag data and logistic regression classification to predict the probability of the movies for a new user. First using alternating least square to extract product feature, and then diminish the feature vector by combining principal component analysis with logistic regression to predict the probability of genres of the movies. Finally, combining the most relevant tags based on similarity score with probability and find top N movies with high scores to the user. The proposed model is assessed using the root mean square error (RMSE), the mean absolute error (MAE), recall@N and precision@N and it is applied to 1M, 10M and 20M MovieLens datasets, resulting in an accuracy of 0.8806, 0.8791 and 0.8739.</p>

Research for Cold-Start Problem in Network-Based Recommendation Algorithm

2013 ◽  
Vol 462-463 ◽  
pp. 861-867
Author(s):  
Li Min Liu ◽  
Chen Yang Zhang ◽  
Zhi Qiang Ma ◽  
Yu Hong Xiao
Keyword(s):  
Cold Start ◽  
Recommendation Algorithm ◽  
New Item ◽  
Cold Start Problem

Network-based recommendation algorithm presents a good recommended result in many aspects. The algorithm is also facing the problem of cold-start. This paper proposes a solution for cold-start problem which makes use of an algorithm based on items similarity to calculate the similarity between the new item and other items in the system, and then link the new item to the user-item matrix. Finally the new items can be recommended to users by the network-based recommendation algorithm what the traditional network-based recommendation algorithm can't do. Therefore, the problem is solved on certain degree.

Sign in / Sign up

Export Citation Format

Share Document