Movie Recommendation via Markovian Factorization of Matrix Processes

Zhang, Richong; Mao, Yongyi

doi:10.1109/access.2019.2892289

Cited by 20 publications

(11 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, Markov processes-based recommendation models can also be enhanced, to some extent, by the Bayesian analysis method for automatic hyper-parameters adjustment. Take MFMP [244] as an instance, which is the probabilistic version of TimeSVD++ [233]. It hypothesizes that the changes of U i (t), V j (t) over time follow the Gaussian Hidden Markov processes rule; so maximizing the posterior distribution can be performed by arg min…”

Section: Models Based On Markov Processesmentioning

confidence: 99%

Recommender systems based on graph embedding techniques: A comprehensive review

Deng

2021

Preprint

View full text Add to dashboard Cite

Recommender systems, a pivotal tool to alleviate the information overload problem, aim to predict user's preferred items from millions of candidates by analyzing observed user-item relations. As for tackling the sparsity and cold start problems encountered by recommender systems, uncovering hidden (indirect) user-item relations by employing side information and knowledge to enrich observed information for the recommendation has been proven promising recently; and its performance is largely determined by the scalability of recommendation models in the face of the high complexity and large scale of side information and knowledge. Making great strides towards efficiently utilizing complex and large-scale data, research into graph embedding techniques is a major topic. Equipping recommender systems with graph embedding techniques contributes to outperforming the conventional recommendation implementing directly based on graph topology analysis and has been widely studied these years. This article systematically retrospects graph embedding-based recommendation from embedding techniques for bipartite graphs, general graphs, and knowledge graphs, and proposes a general design pipeline of that. In addition, comparing several representative graph embedding-based recommendation models with the most common-used conventional recommendation models, on simulations, manifests that the conventional models overall outperform the graph embedding-based ones in predicting implicit user-item interactions, revealing the relative weakness of graph embedding-based recommendation in these tasks. To foster future research, this article proposes constructive suggestions on making a trade-off between graph embedding-based recommendation and the conventional recommendation in different tasks as well as some open questions.

show abstract

Section: Models Based On Markov Processesmentioning

confidence: 99%

Recommender systems based on graph embedding techniques: A comprehensive review

Deng

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Kim et al [4] in 2019, used recurrent Neural Networks which was applied to similar users with similar movie tastes by using Pearson's correlation coefficient to classify them. Zhang et al [6] recommended movies using the Markovian Factorization of Matrix Processes which adapt to a wide range of collaborative filtering problems. Recently, the LSIC model was proposed by Zhao et al [7], which gives the user a ranked list of movies.…”

Section: Literature Surveymentioning

confidence: 99%

Movie Recommendation System Using Bag of Words and Scikit-Learn

Bhattacharya¹,

Lundia²

2019

IJEAST

View full text Add to dashboard Cite

Recommendation systems play an important role in our everyday life. Starting from movie/music streaming sites like Netflix or Spotify to the most basic search engines, the core component is comprised of recommendation systems. Even the technology giant Google is known for its search engine above everything else. To emphasize its importance we aim to build a simple recommendation system using the IMDB movie database. Our finished web application can suggest similar movies based on the input provided by the user, considering factors like the plot of the movie, actors present in it, as well as the director. Needless to say, some factors would be common between the input movie and the recommended ones. The web app uses the scikit-learn python library, to match with the input movie with corresponding movies in the dataset with the highest similarity score. Its frontend is designed using Flask and it is deployed on Heroku. We aim to demystify the magic behind a recommendation system and provide an introduction to natural language processing also on the way.

show abstract

“…Bayesian networks are used (10). Besides, matrix decomposition is used in (11,12) to improve and solve collaborative filtration, a content-based suggestion method.…”

Section: Introductionmentioning

confidence: 99%

User-Oriented Preference Toward a Recommender System

Lin

Arbaiy

2021

Baghdad Sci.J

View full text Add to dashboard Cite

Nowadays, it is convenient for us to use a search engine to get our needed information. But sometimes it will misunderstand the information because of the different media reports. The Recommender System (RS) is popular to use for every business since it can provide information for users that will attract more revenues for companies. But also, sometimes the system will recommend unneeded information for users. Because of this, this paper provided an architecture of a recommender system that could base on useroriented preference. This system is called UOP-RS. To make the UOP-RS significantly, this paper focused on movie theatre information and collect the movie database from the IMDb website that provides information related to movies, television programs, home videos, video games, and streaming content that also collects many ratings and reviews from users. This paper also analyzed individual user data to extract the user's features. Based on user characteristics, movie ratings/scores, and movie results, a UOP-RS model was built. In our experiment, 5000 IMDb movie datasets were used and 5 recommended movies for users. The results show that the system could return results on 3.86 s and has a 14% error on recommended goods when training data as = 50. At the end of this paper concluded that the system could quickly recommend users of the goods which they needed. The proposed system will extend to connect with the Chatbot system that users can make queries faster and easier from their phones in the future.

show abstract

Movie Recommendation via Markovian Factorization of Matrix Processes

Cited by 20 publications

References 42 publications

Recommender systems based on graph embedding techniques: A comprehensive review

Recommender systems based on graph embedding techniques: A comprehensive review

Movie Recommendation System Using Bag of Words and Scikit-Learn

User-Oriented Preference Toward a Recommender System

Contact Info

Product

Resources

About