Company Name Standardization
Budget: €30 – €250 EUR
I am looking for someone (preferably with ML or NLP skills) to standarize company names. Right now, the data has issues concerning punctuation, blanks, corporate forms (e.g. GmbH, KG) etc. Also companies that in theory are the same company are listed as two distinct firms. The aim of this project is to standardize those company names. Ideally, an algorithm would detect similarities across those companies and would harmonize them to one unique company name.
This is what the data is looking like right now:
- 8 Excel files with two columns: 1. column: year 2. column: company name. These excel files correspond to years 2014 - 2021. 2014 for example has 240.000 unique company names
- The data might have punctuation and other issues as mentioned above. After those have been cleaned, the most important point is to harmonize the company names that in theory are one company but are listed as seperate ones. (see screenshot)
Outcome:
- 8 Excel lists with 3 columns
1. column: year, 2. column: old, unstandardized company name, 3. column: new, standardized company name
Looking forward to working with you and let me know if you have any questions!
Best,
Christina
This is what the data is looking like right now:
- 8 Excel files with two columns: 1. column: year 2. column: company name. These excel files correspond to years 2014 - 2021. 2014 for example has 240.000 unique company names
- The data might have punctuation and other issues as mentioned above. After those have been cleaned, the most important point is to harmonize the company names that in theory are one company but are listed as seperate ones. (see screenshot)
Outcome:
- 8 Excel lists with 3 columns
1. column: year, 2. column: old, unstandardized company name, 3. column: new, standardized company name
Looking forward to working with you and let me know if you have any questions!
Best,
Christina