Identifying product opportunities using collaborative filtering-based patent analysis

Abstract

One practical and low-risk approach to product planning for technology-based firms is to identify application products based on their existing product portfolios. Previous studies, however, have tended to neglect the current product development capabilities of target firms and to apply the technical data of specific fields to their methods, thereby failing to quantify a way of identifying various product opportunities. As a remedy, this paper proposes a new multi-step approach to product recommendation. The steps include (1) generating assignee–product portfolio vectors using text mining on a large-scale sample of patents, (2) recommending untapped products for a target firm by using latent Dirichlet allocation and collaborative filtering, (3) producing a visual map based on the promise and domain heterogeneity of the recommended products. To validate the practicability, we applied our approach to a Korean high-tech manufacturer by using all of the patents registered in the United States Patent and Trademark Office database during the period of time from 2009 to 2013. This study contributes to the systematic discovery of new product opportunities across various domains using the existing product portfolios of firms, and could become the basis for a future product opportunity analysis system.