||Semantic Graph Knowledge Repository Based Knowledge Discovery System for Customer Value
122017-03-31 , 法政大学大学院 情報科学研究科
Retail data available for consumer-orientedcompany is a precious asset which can deliver useful insights in decision making and marketing strategy. KID (DataInformation-Knowledge) model is a generic from data toknowledge cognitive model. It bases on how human processoutside information. It can be applied to retail business for supporting retail data analytics. Knowledge repository is a keyelement of KID model. In this paper, a retail semantic graph knowledge repository based knowledge discovery system is proposed and developed for KID model to apply in limited retaildata. The proposed knowledge repository integrates Neo4j graph database, retail ontology designed by Maryam Fazel Zarandi andJess rule engine. It interprets streaming data into meaningful information and assimilate meaningful information into graph knowledge repository to update knowledge by pre-embeddedprior objective-oriented algorithms knowledge in algorithm pool.The deductive reasoning capability is provided by Jess rule engine, so it can deduce answers to retail queries from graph knowledge repository. A customer value assessment case study by using Recency-Frenquecy-Monetary (RFM) analytic model and K-means algorithms is given to demonstrate the proposed semantic graph knowledge repository based knowledge discoverysystem.