Evaluating and ranking patents with multiple criteria: How many criteria are required to find the most promising patents?. (6th April 2019)

• Record Type: Journal Article
• Authors: Ploskas, Nikolaos; Zhang, Tong; Sahinidis, Nikolaos V.; Castillo, Flor; Sankaranarayanan, Krishnan
• Is Part Of: Computers & chemical engineering. Volume 123(2019)
• Page Start: 317
• Page End: 330
• Publication Date: 2019-04-06
• Subjects: Decision support systems -- Multiple criteria analysis -- Text analytics -- Patent rankings -- Optimization; Chemical engineering -- Data processing -- Periodicals; 660.0285
• DOI: 10.1016/j.compchemeng.2019.01.011
• Languages: English
• ISSNs: 0098-1354

Abstract

Highlights: A novel methodology to evaluate and rank patents is proposed. We propose eight criteria to rank patents. An intuitive linear optimization formulation is proposed to determine criteria weights. We automated and tested our methodology in a web-based decision support system. We validate our methodology through several studies in chemical R&D analytics. Abstract: Patents contain a wealth of information about technological progress and market trends. Many existing techniques for patent assessment rely on citation analysis. Despite its importance, citation analysis alone is not adequate to identify all important patents for a given topic. We propose the simultaneous use of eight criteria for patent ranking and evaluation. Additionally, we investigate computationally the effect on ranking quality when fewer than eight criteria are utilized. Contrary to previous approaches, the proposed methodology does not require expert opinions to weigh the different criteria and evaluate the patents. The solution of an intuitive linear optimization problem provides optimal weights for the proposed criteria. These weights are subsequently utilized in a systematic multicriteria methodology for patent ranking. The proposed methodology has been implemented in a web-based decision support system and has been validated in the context of identifying the most important patents for the production of twenty-two chemicals.