1-844-696-6465 (US)        +91 77600 44484        help@dezyre.com
predict-travel-time.jpg

Predict Taxi Trip Duration using Regression, Numpy, Scipy in Pythong

In this challenge, we ask you to build a predictive framework that is able to infer the trip time of taxi rides in Porto, Portugal based on their (initial) partial trajectories. The output of such a framework must be the travel time of a particular taxi t
4.74.7

Users who bought this project also bought

What will you learn

  • Numpy
  • Pandas
  • Scipy
  • Scikit
  • Matplotlib
  • Advance Regression Algorithm
  • Continuous Data

What will you get

  • Access to recording of the complete project
  • Access to all material related to project like data files, solution files etc.

Project Description

The taxi industry is evolving rapidly. New competitors and technologies are changing the way traditional taxi services do business. While this evolution has created new efficiencies, it has also created new problems.

One major shift is the widespread adoption of electronic dispatch systems that have replaced the VHF-radio dispatch systems of times past. These mobile data terminals are installed in each vehicle and typically provide information on GPS localization and taximeter state. Electronic dispatch systems make it easy to see where a taxi has been, but not necessarily where it is going. In most cases, taxi drivers operating with an electronic dispatch system do not indicate the final destination of their current ride.

Another recent change is the switch from broadcast-based (one to many) radio messages for service dispatching to unicast-based (one to one) messages. With unicast-messages, the dispatcher needs to correctly identify which taxi they should dispatch to a pick up location. Since taxis using electronic dispatch systems do not usually enter their drop off location, it is extremely difficult for dispatchers to know which taxi to contact.

To improve the efficiency of electronic taxi dispatching systems it is important to be able to predict the final destination of a taxi while it is in service. Particularly during periods of high demand, there is often a taxi whose current ride will end near or exactly at a requested pick up location from a new rider. If a dispatcher knew approximately where their taxi drivers would be ending their current rides, they would be able to identify which taxi to assign to each pickup request.

The spatial trajectory of an occupied taxi could provide some hints as to where it is going. Similarly, given the taxi id, it might be possible to predict its final destination based on the regularity of pre-hired services. In a significant number of taxi rides (approximately 25%), the taxi has been called through the taxi call-center, and the passenger’s telephone id can be used to narrow the destination prediction based on historical ride data connected to their telephone id.

Instructors

 
Jeeban

Senior Statistical Analyst

"I enjoy 3 things in Analytics - Machine Learning, Image/Video Processing, Natural Language Processing."