Loading Events

Challenges in Analyzing a Two-sided Market and Its Application on Ride-sharing Platform

In this talk, we will introduce a general analytical framework for large scale data obtained from two-sided markets, especially ride-sharing platforms like DiDi. This framework integrates classical methods including Experiment Design, Causal Inference and Reinforcement Learning, with modern machine learning methods, such as Graph Convolutional Models, Deep Learning, Transfer Learning and Generative Adversarial Network. We aim to develop fast and efficient approaches to address five major challenges for ride-sharing platform, ranging from demand-supply forecasting, demand-supply diagnosis, MDP-based policy optimization, A-B testing, to business operation simulation. Each challenge requires substantial methodological developments and inspires many researchers from both industry and academia to participate in this endeavor. Based on our preliminary results for the policy optimization challenge, we receive the Daniel Wagner Prize for Excellent in Operations Research Practice in 2019. All the research accomplishments presented in this talk are joint work by a group of researchers at Didi Chuxing and our collaborators.

Register for the event on Eventbrite.

Challenges in Analyzing a Two-sided Market and Its Application on Ride-sharing Platform

Event Details

Venue

December 5, 2019 @ 11:00 am - 12:00 pm

Venue

Bahen Centre for Information Technology, Room 1200

In this talk, we will introduce a general analytical framework for large scale data obtained from two-sided markets, especially ride-sharing platforms like DiDi. This framework integrates classical methods including Experiment Design, Causal Inference and Reinforcement Learning, with modern machine learning methods, such as Graph Convolutional Models, Deep Learning, Transfer Learning and Generative Adversarial Network. We aim to develop fast and efficient approaches to address five major challenges for ride-sharing platform, ranging from demand-supply forecasting, demand-supply diagnosis, MDP-based policy optimization, A-B testing, to business operation simulation. Each challenge requires substantial methodological developments and inspires many researchers from both industry and academia to participate in this endeavor. Based on our preliminary results for the policy optimization challenge, we receive the Daniel Wagner Prize for Excellent in Operations Research Practice in 2019. All the research accomplishments presented in this talk are joint work by a group of researchers at Didi Chuxing and our collaborators.

Register for the event on Eventbrite.

Upcoming Events

All
  • All
  • Alumni events
  • Anti-Racism and Cultural Diversity Office events
  • Convocation events
  • Faculty & staff events
  • Holidays
  • Info sessions
  • Lectures, seminars and workshops
  • Socials
  • U of T holidays & closures

Academic/Student Registration – 2025 CRAFT Microfluidics Professional Course

Wed July 9, 2025 @ 8:30 am - Fri July 11, 2025 @ 5:30 pm
The 2025 Microfluidics Professional Course is designed as a crash course for industrial researchers with little or no experience in the microfluidics field. It is open to international attendees and will include...

2025 Toronto Robotics Conference

Tue July 15, 2025 @ 9:00 am - Wed July 16, 2025 @ 4:00 pm
Join the University of Toronto Robotics Institute’s expert network at the University of Toronto Mississauga on July 15 and 16 for a two-day, dual-track showcase of the latest AI-robotics research...

U of T Alumni x Featherstone Estate Winery Event

Thu July 17, 2025 @ 5:00 pm - 9:00 pm
  Located in the beautiful setting of Niagara wine country, Featherstone Estate Winery—owned by close friends of the university Rayla and George Myhal (U of T Engineering)—will open its doors for an unforgettable alumni celebration.  ...

Presidential Day

Fri August 1, 2025
The university will be closed.