/Widebot_Task2

Primary LanguageJupyter Notebook

Binary Classification Task

Fun Results:

  • EDA (Exploratory Data Analysis) significantly reduced the problem and made it very simple.
  • EDA enabled creation of a 1 line python model was created and achieved the same performance as SVM and logistic regression (85% validation accuracy).
  • Simple API (not very needed) was created, can be accessed here
  • To use the API, an API key is needed (sent by email)
  • Insights into how the data was generated (it was most probably synthetic) and how many variables were created