R&D proposal screening system based on text-mining approach
by Changwoo Choi, Yongtae Park
International Journal of Technology Intelligence and Planning (IJTIP), Vol. 2, No. 1, 2006

Abstract: With the enormous accumulation of R&D projects, it becomes very difficult to avoid their duplication; thus, the screening process of R&D proposals must rest on intelligent systems, rather than on intuitive criteria. This is particularly obvious for large-scale, multi-product firms that deal with multi-technology R&D projects. However, previous research on R&D knowledge management has focused on the ex post facto project evaluation/selection stage, instead of the preliminary screening stage. In this research, we propose an intelligent and systematic R&D proposal screening system that may be employed to identify and filter out duplications of previous or ongoing projects. The screening algorithm is based on the coherence of contents and substance, not on the coincidence of titles, between a new R&D proposal and the pool of completed and existing R&D projects. The text-mining methodology is employed to this end. An illustrative set of real data is applied to elucidate the detailed procedure of the system.

Online publication date: Thu, 27-Jul-2006

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Technology Intelligence and Planning (IJTIP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com