Rawahi, Sanaa Saeed Musallam Al <br/><br/>
DAILY CONSUMER PURCHASE SUGGESTED LIST BY RECOMMENDED SYSTEM / 
SANAA SAEED MUSALLAM AL RAWAHI; SUPERVISOR: PROF. DR. ERBUĞ ÇELEBİ 
 - 78 sheets;  31 cm.  Includes CD 
<br/><br/> Includes bibliography (sheets 75-78) 
<br/><br/>Thesis (MSc) Cyprus International University. Institute of Graduate Studies and Research Information Technologies Department 
<br/><br/>Includes bibliography (sheets 75-78) 
<br/><br/> ABSTRACT<br/>The aim of this study is to use algorithms to build a recommender <br/>system that can generate a suggestion for consumer shopping list. <br/>We analyzed the effectiveness of a recommender system using three <br/>different methods collaborative filtering (CF), Content-based <br/>filtering (C-B) and Hybrid). We investigate and test each approach <br/>of the recommended system. Next we have evaluated the accuracy <br/>of the system using Recall@5 scored 79% for popularity and 67% <br/>for CF. Recall@10 scored for popularity and CF 91% and 79% <br/>respectively, Precision@5 scored 77% and 75% for Hybrid and CF <br/>approaches Precision@10 scored 88% for Hybrid and 82% for CF. <br/>The harmonic evaluation for both Recall and Precision F1@10 <br/>scored 88% and 80% for CF and Hybrid approach. Finally, we <br/>observe that the content-based scored the lowest which is we <br/>conclude that it is superior to CF for typical consumer purchases. <br/>We observed that hybrid approach provides the best results for <br/>making recommendations to brand-new users with no prior <br/>information.<br/>Keywords: Collaborative Filtering, Content-Based Filtering, Hybrid <br/>Filtering, Precision, Recall, Recommendation System 
<br/><br/><label>Subjects--Topical Terms: </label><br/>Recommender systems (Information filtering) --Dissertations, Academic