Insurance recommendation engine using a combined collaborative filtering and neural network approach

 

Show simple item record

dc.contributor.advisor Er, Sebnem
dc.contributor.advisor Clark, Allan
dc.contributor.author Pillay, Prinavan
dc.date.accessioned 2021-09-15T15:22:12Z
dc.date.available 2021-09-15T15:22:12Z
dc.date.issued 2021_
dc.identifier.citation Pillay, P. 2021. Insurance recommendation engine using a combined collaborative filtering and neural network approach. . ,Faculty of Science ,Department of Statistical Sciences. http://hdl.handle.net/11427/33924 en_ZA
dc.identifier.uri http://hdl.handle.net/11427/33924
dc.description.abstract A recommendation engine for insurance modelling was designed, implemented and tested using a neural network and collaborative filtering approach. The recommendation engine aims to suggest suitable insurance products for new or existing customers, based on their features or selection history. The collaborative filtering approach used matrix factorization on an existing user base to provide recommendation scores for new products to existing users. The content based method used a neural network architecture which utilized user features to provide a product recommendation for new users. Both methods were deployed using the Tensorflow machine learning framework. The hybrid approach helps solve for cold start problems where users have no interaction history. The accuracy on the collaborative filtering produced 0.13 root mean square error based on implicit feedback rating of 0-1, and an overall Top-3 classification accuracy (ability to predict one of the top 3 choices of a customer) of 83.8%. The neural network system achieved an accuracy of 77.2% on Top-3 classification. The system thus achieved good training performance and given further modifications, could be used in a production environment.
dc.subject Statistical Sciences
dc.title Insurance recommendation engine using a combined collaborative filtering and neural network approach
dc.type Master Thesis
dc.date.updated 2021-09-15T02:22:52Z
dc.language.rfc3066 eng
dc.publisher.faculty Faculty of Science
dc.publisher.department Department of Statistical Sciences
dc.type.qualificationlevel Masters
dc.type.qualificationlevel MSc
dc.identifier.apacitation Pillay, P. (2021). <i>Insurance recommendation engine using a combined collaborative filtering and neural network approach</i>. (). ,Faculty of Science ,Department of Statistical Sciences. Retrieved from http://hdl.handle.net/11427/33924 en_ZA
dc.identifier.chicagocitation Pillay, Prinavan. <i>"Insurance recommendation engine using a combined collaborative filtering and neural network approach."</i> ., ,Faculty of Science ,Department of Statistical Sciences, 2021. http://hdl.handle.net/11427/33924 en_ZA
dc.identifier.vancouvercitation Pillay P. Insurance recommendation engine using a combined collaborative filtering and neural network approach. []. ,Faculty of Science ,Department of Statistical Sciences, 2021 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/33924 en_ZA
dc.identifier.ris TY - Master Thesis AU - Pillay, Prinavan AB - A recommendation engine for insurance modelling was designed, implemented and tested using a neural network and collaborative filtering approach. The recommendation engine aims to suggest suitable insurance products for new or existing customers, based on their features or selection history. The collaborative filtering approach used matrix factorization on an existing user base to provide recommendation scores for new products to existing users. The content based method used a neural network architecture which utilized user features to provide a product recommendation for new users. Both methods were deployed using the Tensorflow machine learning framework. The hybrid approach helps solve for cold start problems where users have no interaction history. The accuracy on the collaborative filtering produced 0.13 root mean square error based on implicit feedback rating of 0-1, and an overall Top-3 classification accuracy (ability to predict one of the top 3 choices of a customer) of 83.8%. The neural network system achieved an accuracy of 77.2% on Top-3 classification. The system thus achieved good training performance and given further modifications, could be used in a production environment. DA - 2021_ DB - OpenUCT DP - University of Cape Town KW - Statistical Sciences LK - https://open.uct.ac.za PY - 2021 T1 - Insurance recommendation engine using a combined collaborative filtering and neural network approach TI - Insurance recommendation engine using a combined collaborative filtering and neural network approach UR - http://hdl.handle.net/11427/33924 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record