NYC Taxi Travel Time Prediction through Leveraging Geographical Information

Jan 7, 2020
PDF Code Poster

Location

This project was done as a course project for 10-701: Introduction to Machine Learning in the Fall ‘19 term at CMU.

Details

We present a method of leveraging known geographical separations to better estimate travel times by car between two points in a city, specifically New York City. This allows for the creation of multiple simpler models that can be combined into an ensemble by taking advantage of information about possible crossing points.

We primarily used two modelling techniques:

  • Gradient Boosted Regression trees using XGBoost
  • Deep neural networks using Tensorflow
research machine-learning
Avatar
Amrit Singhal
MS in Machine Learning

My research interests include machine learning, reinforcement learning and artifical intelligence.

Related