I am looking to take a large single dataset of approximately ~100,000 company names and organize them into industry, sector, and sub-sectors. The reason we want to do this is to know which companies operate in which sectors.
The two main phases I believe are to analyze all the text of all the companies and develop i) a hierarchical structure of the industries and sectors and ii) fit the companies into those sectors. In terms of assisting the structuring beyond just text analysis of the descriptions, I can provide:
1. About 30,000 companies already are categorized into ~80 sectors, sub-sectors, etc. to give you an idea of the type of organization. However, take caution, some of these categorizations may be incorrect. Also, many of these categories need to be broken down into far more detailed categories.
2. Standalone market structures of certain markets that were built by third party organizations.
3. Suggestions for some sector names
Please see below dropbox link for further summary and sample files:
[url removed, login to view]
6 freelance ont fait une offre moyenne de 1041 $ pour ce travail
PMP, MBA and professional data analyst here. Worked with large and complex data sets in Excel, Tableau, SPSS etc. to generate reports, analysis and presentation.