Predicting Where The Traffic Will Flow

"Using historical traffic data and real-time traffic input from the Singapore Land Transport Authority (LTA)'s i-Transport system, IBM's Traffic Prediction Tool predicted traffic flows over pre-set durations (10, 15, 30, 45 and 60 minutes). Overall prediction results were well above the target accuracy of 85 percent. With these predictions, LTA's traffic controllers will be able to anticipate and better manage the flow of traffic to prevent the build-up of congestion.

At a global level, this innovative use of technology represents another option in the response to the complexity of mega-urban congestion, especially in the developing world.

While infrastructure growth is required in many cities, it cannot be the only solution to congestion given the significant budgetary, social and environmental costs. IBM believes innovation can and needs to be applied to the challenge of mega-urban congestion. For example, technologies such as the Traffic Prediction Tool enable more intelligent use of a city's existing infrastructure."