DSpace Repository

Using Video Analytics to Solve the Cold Start Problem in Recommendation Systems

Show simple item record

dc.contributor.advisor Dailey, Matthew N.
dc.contributor.author Panta, Subigya Jyoti
dc.contributor.other Mongkol, Ekpanyapong
dc.contributor.other Dung, Phan Minh
dc.date.accessioned 2018-05-23T03:50:46Z
dc.date.available 2018-05-23T03:50:46Z
dc.date.issued 2018-05
dc.identifier.other AIT
dc.identifier.uri http://www.cs.ait.ac.th/xmlui/handle/123456789/898
dc.description 56 p. en_US
dc.description.abstract In this thesis, I use video analytics to obtain age and gender of a person and use this information to help bootstrap a recommendation system to overcome the well-known cold start problem. I perform a comparative study of recommendations produced with age and gender alone versus recommendations produced by collaborative filtering with data collected manually by survey. One hundred and thirty participants took part in the survey, in which they gave ratings to items on scale of 1 to 5. Collaborative filtering is a standard method for recommendations based on similarity of users and items using a variety of models. For the case study, I focus on purchase of drinks such as tea, coffee, frappes and smoothies at a coffee shop at AIT. The coffee shop has 41 different menu items; the system predicts users' ratings for menu items by combining traditional collaborative filtering measurements obtained through survey methods with the demographic data available from video analytics. The top n predicted ratings are given as recommendations to new customers. To evaluate each method, I use an approach I call "Pop and Predict," in which I remove a known rating from the rating matrix, predict the rating, and then calculate the root mean squared error between predicted ratings and the original ratings. For baseline error, I use root mean squared error between the global and local means and predicted ratings. For comparison, I use root mean squared error obtained by collaborative filtering. Then I use models such as neural networks and SVMs in conjunction with video analytics and obtain the root mean squared error for these models. I compare the error rates obtained by each approach. I find that using only age and gender for prediction produces poor results: it is worse than global mean. However, age and gender combined with ingredients in the menu item and contextual information such as time of the day (morning, afternoon, evening, night) lead to much better results. en_US
dc.description.sponsorship AIT Fellowship en_US
dc.language.iso en en_US
dc.publisher AIT en_US
dc.subject recommendation en_US
dc.subject recommender en_US
dc.subject video analytics en_US
dc.subject cold start en_US
dc.subject recommendation system en_US
dc.subject recommender system en_US
dc.subject recommendation system with video analytics en_US
dc.subject recommender system with video analytics en_US
dc.subject solving cold start problem in recommendation system en_US
dc.subject solving cold start with video analytics en_US
dc.title Using Video Analytics to Solve the Cold Start Problem in Recommendation Systems en_US
dc.type Thesis en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account