Could data mining prevent another 60-mile traffic jam?

China may have recently gained the honor of officially becoming the world's second-largest economy, and with that honor also came some of the spoils -- including the world's most gigantic traffic jam. A 60-mile gridlock extending from Beijing to the reaches of Inner Mongolia. (The latest report say the jam-up has vanished, somehow.)

Perhaps Chinese planners could look south, to Singapore, for ways technology and analytics can help tamp down the likelihood of such incidents. In Singapore controllers receive real-time data through sensors to model and predict future traffic flows “with 90% accuracy.”

The experiences of Singapore and other cities were examined in a recent report from IBM, which explores how transportation officials are now able to collect real-time data on traffic conditions and instantaneously analyze that data and deploy strategies that minimize delays and congestion. Thanks to the proliferation of data-gathering devices on our roads and recent advances in business analytics -large volumes of data can be quickly synthesized and actionable insights extracted that allow for active management of our transportation networks to keep people moving more efficiently.

New approaches to traffic management is also being developed through crowdsourcing. Witness the current data mining competition being held as part of IEEE International Conference on Data Mining 2010 (ICDM), being held in Sydney, Australia, this December. Sponsored by TomTom, the competition, which closes September 6th for entries, seeks solutions that enable the "prediction of city traffic based on simulated historical measurements or real-time stream of notifications sent by individual drivers from their GPS navigators." Prizes worth $5,000 will be awarded to the winners.

Contest organizers are asking researchers to devise algorithms that tackle problems of traffic flow prediction, for the purpose of intelligent driver navigation and improved city planning. This may be the only way to untangle the scourge of urban gridlock, organizers say: "Complexity of processes that stand behind traffic flow is so large, that only data mining algorithms - from the domains of structure mining, graph mining, data streams, large-scale and temporal data mining - may bring efficient solutions for these problems."

Readers, if your were asked for ways to prevent 60-mile traffic jams -- or at least keep them to manageable 30-mile gridlocks -- what would you recommend? Is data mining, as ICDM contest organizers suggest, the only way out, or are there other alternatives?

This post was originally published on Smartplanet.com