How it Works

TaxiSG is a Big Data solution for taxi fleets. It uses advanced algorithms and powerful big data infrastructure to distill insights and analysis from real time data. It consists of two parts - an analytics dashboard that captures performance metrics and consumer experience in real time and a driver app that increases fleet efficiency and profitability by directing taxis to areas of high unmet demand.

  • Real time taxi data is automatically uploaded to our cloud platform
  • Machine learning algorithms predict real time unmet taxi demand
  • Fleet performance is tracked on our web based analytics dashboard

Demand Heatmaps

See where taxis are needed right now on a real time heatmap.

Machine Learning

Use machine learning techniques to predict unmet demand.

Driving Directions

Get traffic aware driving directions to high demand areas

Reduce time spent in queue

Get directions to nearby taxi stands with short wait times

Clean Design

Optimized for iOS7 on iPhone and iPad. Beautiful and easy to use UI.

Absolutely Free

Free download from the App Store. No monthly fees.

Dashboard

Big Data Analytics for your Taxi Fleet

The TaxiSG dashboard builds a layer of optimization and intelligence on top of GPS data already generated by your fleet. Why rely on opinion and intuition? Use our visually stunning interface to gain broader insight into taxi fleet performance, profitability, and quality of service, without having to write code.

Because it operates entirely in the cloud, your data can be accessed securely on any browser, tablet or smart phone.

  • Quantify taxi availability and demand
  • Pinpoint unmet taxi demand in real time
  • Monitor occupancy and driving distance

App Demo

Taxi drivers can use our iPhone app to visualize unmet demand in real time.

12:00

00
06
12
18
24

API

Heat Maps

Taxi Demand Heatmap
http://taxisg.io/pickups.json?zoom={ZOOM_LEVEL}&time={ddd} {mmm} {dd} {yyyy} {hh}:{nn}:{ss} GMT+0800 (SGT)

Graphs

Taxi Demand (Week)
http://taxisg.io/admin/grid/12/{GRID_ID}.json?from={yyyy}_{mm}-{dd}&to={yyyy}-{mm}-{dd}
Taxi Demand (Location)
http://taxisg.io/admin/grid/12/{GRID_ID_0}/{GRID_ID_1}/{GRID_ID_2}?date[]={yyyy}-{mm}-{mm}
Driving Distance (Fleet)
http://taxisg.io/admin/distances/d3.json?from_date={yyyy}-{mm}-{dd}&type=discrete

Daniela Rus is a Professor of Electrical Engineering and Computer Science and Director of the Computer Science and Artificial Intelligence Laboratory at MIT. Her research interests include distributed robotics, mobile computing and programmable matter.


Afian Anwar is a computer scientist at MIT, where he works at the Computer Science and Artificial Intelligence Lab. His general research interests involve applying computer science and operations research methods and algorithms to solve large scale transportation problems.


Mikhail Volkov is a graduate student in Electrical Engineering and Computer Science at MIT. His research interests are in computer vision, machine learning and semantic compression algorithms for Big Data Applications.


Gavin Hall is a graduate student in Mechanical Engineering at MIT. He has worked at NASA's Jet Propulsion Laboratory and the Johns Hopkins University Applied Physics Laboratory. His research interests include cooperative control and estimation in multi-robot systems.