Skip to content

Latest commit

 

History

History
14 lines (11 loc) · 505 Bytes

README.md

File metadata and controls

14 lines (11 loc) · 505 Bytes

twosigma_ml

Predicting 'interest level' in NY listings using machine learning

This is a dataset from a competition on Kaggle. The aim is to predict 'interest level' in rental listings. It is a classification problem.

Features explored -

  1. Number of bedrooms
  2. Number of bathrooms
  3. Description
  4. Number of photos
  5. Location of listing
  6. Price point of listing

Based on these features, I trained a LR, Random forest and QDA model. The Random forest model has displayed the best performance.