Exploiting Knowledge Graphs for Facilitating Product/Service Discovery

TL;DR

This paper introduces an unsupervised, knowledge graph-based method for product discovery that improves interoperability and reduces manual labeling costs by organizing products in a unified semantic framework.

Contribution

It presents a novel architecture leveraging OWL and knowledge graphs for cost-effective, semantic product classification and matching in e-commerce.

Findings

Effective product categorization using knowledge graphs

Improved matching accuracy for product recommendations

Cost reduction in data labeling processes

Abstract

Most of the existing techniques to product discovery rely on syntactic approaches, thus ignoring valuable and specific semantic information of the underlying standards during the process. The product data comes from different heterogeneous sources and formats giving rise to the problem of interoperability. Above all, due to the continuously increasing influx of data, the manual labeling is getting costlier. Integrating the descriptions of different products into a single representation requires organizing all the products across vendors in a single taxonomy. Practically relevant and quality product categorization standards are still limited in number; and that too in academic research projects where we can majorly see only prototypes as compared to industry. This work presents a cost-effective solution for e-commerce on the Data Web by employing an unsupervised approach for data classification and exploiting the knowledge graphs for matching. The proposed architecture describes available products in web ontology language OWL and stores them in a triple store. User input specifications for certain products are matched against the available product categories to generate a knowledge graph. This mullti-phased top-down approach to develop and improve existing, if any, tailored product recommendations will be able to connect users with the exact product/service of their choice.