SUGGEST RECOMMENDATION FOR LIBRARY USERS USING GRAPHS
Abstract
The aim of this paper is to prove the usefulness of graphs in solving an ever-present problem for library users: finding books they like and they are looking for. Graphs are known as an important tool in solving conditioned optimization problems. We propose a graph-based system of recommendation which can be easy used in a library for assisting and helping users in finding in real time the books they like. The main advantage of the proposed graph-based approach lies in the ease with which new data or even new entities from different sources are added to the graph without disturbing the entire system. The system uses the similarity scores in order to find the similarity between objects and to get the best recommendation for a user's request. In the end, we will compare the results from used formulas.References
Sales force, Product Recommendation Engines to Improve Customer Relationships, https://www.salesforce.com/solutions/industries/retail/resources/product-recommendation-engines , (accessed 16 March 2019).
Microsoft, Create a graph database and run some pattern matching queries using T-SQL, https://docs.microsoft.com/en-us/sql/relational-databases/graphs/sql-graph-sample?view=sql-server-2017 , (accessed 16 March 2019).
Valiance Solutions, RECOMMENDER SYSTEMS 101, https://valiancesolutions.com/recommender-systems-101 , (accessed 16 March 2019).
Wikipedia, Cypher Query Language, https://en.wikipedia.org/wiki/Cypher_Query_Language , (accessed 16 March 2019).
Jonathan L. Gross, Jay Yellen (2004). Handbook of Graph Theory, CRC Press
Junmei Feng , Xiaoyi Fengs, Ning Zhang, Jinye Peng (2018). An improved collaborative filtering method based on similarity, https://doi.org/10.1371/journal.pone.0204003
Guy, N. N. (2017). A Recommender system for rental properties (Thesis). Strathmore University
