Ford’s been grabbing headlines recently with its broad Smart Mobility initiative–the basis for its advances in connectivity, mobility, and autonomous vehicles. Now, the automaker is tapping IBM to move the project forward with cloud-based analytics.

On Monday, Ford and IBM announced they are developing a pilot platform that analyzes vehicular data. It uses small chunks (10-15 sec) of data, and the patterns it sees in that data, to help drivers find a parking spot in a crowded lot or avoid a traffic jam on their drive home from work.

Dubbed Ford’s Smart Mobility Experimentation Platform, it’s currently supporting the company’s Dynamic Shuttle program in Dearborn, Michigan that Ford moved into pilot late last year. If one shuttle is out of commission, the Smart Mobility platform will route transportation requests to other shuttles that it knows to be in service–in theory, keeping everyone on time.

As patterns change and shift, so does the analysis of those patterns. To keep up with these changes, the platform uses IBM’s cloud to stream the updated analytics.

Take the parking lot situation, for example. Once a driver starts the car and backs out of a space, other drivers nearby would be alerted that the space had been vacated. The nearby motorists would also be told where the space was located so they didn’t have to waste fuel driving around the lot looking for one.

“Ford is transforming from being a producer of automobiles, to also becoming a provider of mobility solutions. Working with IBM, Ford can use data and real-time streaming analytics in the cloud to improve the commuting experience for its customers,” said Randy Cox, Ford lead account partner for IBM Global Business Services.

In an IBM press release, the company compared the technology to the platform used by the stock market to predict when to buy or sell a stock, and to tools used by the energy industry to predict outages and deploy crews. However, it’s not just for commuters who are traveling by car.

The project could work with different forms of travel as well. By taking data from the proper feeds, the system could be alerted of a problem on a bus line or subway system and recommend that the commuter take a cab or bicycle to work that day.