Summer Research Fellowship Programme of India's Science Academies

Intellectual Asset Valuation – A Big Data Analytics

Dr. Kutty Kumar

Assistant Professor, Library and Information Science, College of Veterinary Science, Sri Venkateswara Veterinary Unviersity, Proddatur 516360.

Dr. Ramesh Venkadachalam

Assistant Professor, School of Mathematics & Computer Science, Central University of Tamil Nadu, Thiruvarur.


Big data, a platform that requires enhanced decision making, are prevalent in almost every field of manufacturing and operates towards next generation innovative technologies. In this project, we attempt to use big data analytics on Intellectual asset valuation. In simple words, given an intellectual property or a set of Intellectual properties, we aim to develop a platform which can identity its adjacencies. Adjacency identification is one of the key parameters for a vibrant market player and also to define the future direction of any given company/organization. We identified a patent published in 1979 (seminal) by a dominant player and we collected the first 3 generations of cited patents. In the first generation, there were 39 patents citing the seminal patent, in the second generation there were 2158 patents citing the 39 patents in the first generation and we are attempting to collect the next one or two generations. These data are extracted in the CSV (Comma-Separated Values) file format. The data predominantly includes forward citations, backward citations, the International Classification Codes, the Cooperative Patent Classification, patent family information, number of dependent and independent claims, geographical coverage, number of inventors, geography of the patent applicant and prosecutions history, to list a few. The number of classification codes and the width of its coverage is expected to play a vital role in our analytics. Further, the aim here is to use big data tools on categorizing the 3rd generation citation patents to identify the adjacencies of the first generation patent we started with. Trivially one may classify the given set of patents in any generation based on their international classification codes. We aim to deploy some big data analytics tools to design a better classification which will help to identify the adjacencies.

Keywords: patent, classification code, inventors, citation, generations

Written, reviewed, revised, proofed and published with