acm-header
Sign In

Communications of the ACM

ACM TechNews

The Seesaw of Supply and Demand


View as: Print Mobile App Share:
Singapore Management University assistant professor Pradeep Varakantham.

Singapore Management University assistant professor Pradeep Varakantham uses techniques from artificial intelligence, machine learning, operations research, and behavioral economics to made supply with demand for complex urban challenges.

Credit: Cyril Ng

Singapore Management University professor Pradeep Varakantham dynamically and continuously matches supply with demand to tackle complex urban challenges, using diverse techniques from artificial intelligence, machine learning, operations research, and behavioral economics.

"Since we have large data sets for these matching problems, they provide ideal settings for us to understand the potential impact of our research on real-world problems," Varakantham notes.

Once a problem has been identified, the professor builds a model that best represents the available data, and applies it toward acquiring the best supply/demand matching strategies, which are tested on real-world data or a simulated data set. An example of this process was the development of a model and matching algorithms for optimally pairing ambulances with base stations to enable faster emergency response, using data from the Singapore Civil Defense Force. Another initiative focused on scheduling traffic police patrols, and Varakantham says he used game theory to model randomized patrols.

He notes a key challenge in his work is demand prediction, since there is not always sufficient data to make strong predictions.

Varakantham thinks accuracy can be enhanced by combining machine-learning methods and more sensors. "The vision is to build a coordinated Internet of Things and people through the use of smart 'matching' algorithms that is extremely efficient," he says.

From Research@SMU
View Full Article

 

Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account