Skip to content

Latest commit

 

History

History
10 lines (8 loc) · 783 Bytes

README.md

File metadata and controls

10 lines (8 loc) · 783 Bytes

Litigation risk analyzer

In this project we try to analyze potential rival companies for a specific company which may in future sue them and run into litigation issues. The prior prediction of potential rivals who are working in the same feild can be of great help especially in terms of being aware and being prepared what can come next. The analysis is done from a corpus of collected documents of patents by various companies and then doing sophisticated text preprocessing and analysis using NLP, topic modeling on them.

Technical summary of the work done:

a. Identifying the top 40 topics using NMF and LDA.
b. Doing a Hierarchical cluster of companies based on text similarity of patents.
c. Creating a MDS map of the companies using text similarity.