dc.contributor.author |
Shafin, Shadman |
|
dc.date.accessioned |
2019-07-04T08:36:00Z |
|
dc.date.available |
2019-07-04T08:36:00Z |
|
dc.date.issued |
2018-12 |
|
dc.identifier.uri |
http://hdl.handle.net/123456789/2695 |
|
dc.description.abstract |
Many E-commerce, Social Network, Entertainment sites uses recommendation system frequently to increase their revenue. There are various methods of recommending an item to a specific user. Collaborative filtering, content-based filtering are very popular. Matrix factorization is one of the most widely used method to predict the ratings of an item whether to recommend it to a user or not. But traditional matrix factorization only considers the user-item ratings matrix. It doesn’t consider any extra information about any user or any item. Sometimes the information associates with the item or user is very important to predict a rating of item by a particular user. To do so, I propose a model which will consider the textual information about items and users provided with the dataset. Thus it will be helpful to design a better and more accurate recommendation system which will give almost accurate prediction of a missing rating. |
en_US |
dc.language.iso |
en_US |
en_US |
dc.publisher |
Daffodil International University |
en_US |
dc.relation.ispartofseries |
;P12208 |
|
dc.subject |
Computer Science & Engineering |
en_US |
dc.subject |
Dataset |
en_US |
dc.title |
Building a Movie Recommendation System Using Non Negative Regularized Matrix Factorization on Movie Lens Dataset |
en_US |
dc.type |
Other |
en_US |