Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Insurance recommendation engine using a combined collaborative filtering and neural network approach
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 col...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Statistical Sciences
2021
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613286852198400 |
|---|---|
| access_status_str | Open Access |
| author | Pillay, Prinavan |
| author2 | Er, Sebnem |
| author_browse | Er, Sebnem Pillay, Prinavan |
| author_facet | Er, Sebnem Pillay, Prinavan |
| author_sort | Pillay, Prinavan |
| collection | Thesis |
| description | 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. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/33924 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:33:43.673Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2021 |
| publishDateRange | 2021 |
| publishDateSort | 2021 |
| publisher | Department of Statistical Sciences |
| publisherStr | Department of Statistical Sciences |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/33924 Insurance recommendation engine using a combined collaborative filtering and neural network approach Pillay, Prinavan Er, Sebnem Clark, Allan Statistical Sciences 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. 2021-09-15T15:22:12Z 2021-09-15T15:22:12Z 2021 2021-09-15T02:22:52Z Master Thesis Masters MSc http://hdl.handle.net/11427/33924 eng application/pdf Department of Statistical Sciences Faculty of Science |
| spellingShingle | Statistical Sciences Pillay, Prinavan Insurance recommendation engine using a combined collaborative filtering and neural network approach |
| thesis_degree_str | Master's |
| title | Insurance recommendation engine using a combined collaborative filtering and neural network approach |
| title_full | Insurance recommendation engine using a combined collaborative filtering and neural network approach |
| title_fullStr | Insurance recommendation engine using a combined collaborative filtering and neural network approach |
| title_full_unstemmed | Insurance recommendation engine using a combined collaborative filtering and neural network approach |
| title_short | Insurance recommendation engine using a combined collaborative filtering and neural network approach |
| title_sort | insurance recommendation engine using a combined collaborative filtering and neural network approach |
| topic | Statistical Sciences |
| url | http://hdl.handle.net/11427/33924 |
| work_keys_str_mv | AT pillayprinavan insurancerecommendationengineusingacombinedcollaborativefilteringandneuralnetworkapproach |