Applications of Machine Learning for Startups Success Prediction in Venture Capital
Research conducted as part of a master's thesis project
The Data folder contains the various CSV files which were part of the Crunchbase dataset including two datasets seperated into American and European startups only after initial cleaning
The Data_Cleaning_VC.ipynb file contains most of the data cleaning aspects of this project.
Modelling_VC.ipynb contains further data transformation, scaling, encoding and the final model building and testing with the various metrics extractions
Modelling_getDummies.ipynb contains an alternative approach through get_dummies encoding to keep all data as Pandas DataFrames throughout