Date of Degree
Data Analysis & Visualization
Deduplication, New York, Political Donors
Starting with the publicly available data from the New York State Board of Elections, this project first explored the best data processing and algorithmic parameters by which to match the donors. Once an optimal algorithm was generated, the donors were matched in two separate groups: organizations and individuals. The database that stores the matched donors is a product also of this project, with the hope that it will be used by local reporters and advocacy organizations.
Wilde, Annalisa, "Who Pays? New York State Political Donor Matching with Machine Learning" (2021). CUNY Academic Works.
Zipfile of github repository of python scripts
ny_campaign_finance_database_01_14_21.tar.partaa (1024000 kB)
Part 1 of final database archive
ny_campaign_finance_database_01_14_21.tar.partab (1024000 kB)
Part 2 of final database archive
ny_campaign_finance_database_01_14_21.tar.partac (1024000 kB)
Part 3 of final database archive
ny_campaign_finance_database_01_14_21.tar.partad (1996 kB)
Part 4 of final database archive