There’s no shortage of data when it comes to transportation. Mountains of it are being generated by buses and trains, cars, roads, sensors, parking meters, signals – you name it. Add in the constraints of the system and the realities of your infrastructure and it can seem like a never-ending race to keep the trains and buses running on time or the traffic running smoothly. Advanced technologies are already making transportation smarter – from algorithms that can help predict when and where traffic will occur before it’s a problem to software that can help determine when to take a train care out of service for maintenance before an issue develops. But what does the future hold? A glimpse can be seen this week in what’s sure to be a battle for the ages. An IBM computing system named Watson is taking on two of the greatest champions – Ken Jennings and Brad Rutter – on one of America’s most popular quiz shows "Jeopardy!." It’s about more than winning a game. Watson represents a huge leap forward for how we can manage and make sense of massive amounts of information. With the ability to analyze the meaning and context of human language and quickly process information to suggest answers to questions posed in natural language, it has the potential applications in many fields including transportation. Watson-like capabilities can help transportation operators make more informed decisions, in real-time, faster than traffic on a good day. Perhaps the technology could even enable commuters to ask - what's the best way to get from point A to point B? Snow, ice, rain. Inclement weather means that travel patterns can be vastly different than on a normal day. The peak period of capacity can quickly shift – typically busy roads are empty or a quiet subway is now packed. A system with Watson’s capabilities could help an operator quickly determine the right amount of train cars, how to manage traffic flow or recommend the best way to alter the bus or commuter rail schedule to handle the quickly changing travel patterns. You get off the bus and see the train heading out of the station. It’s happened to all of us. The ability to seamlessly coordinate inter-modal transportation is a tough balance between schedules, the number of potential passengers and more. Watson-like capabilities could help operators see patterns in the traffic and real-time information based on current passenger demand to ask things like: “What happens if we delay this train for a minute or two because the bus that most of our passengers use to get to this station is running late and the next train isn’t for 20 minutes?” Even as commuters, we experience information overload. Today we can look through publically available transit schedules, where road work is happening, real-time updates from traffic sites, travel providers and search engines. On top of that, any number of social media tools like Facebook, Twitter or Roadify can report on how traffic is at a moment in time. A Watson-like technology could be integrated with all of these streams of structured and unstructured data and into the transportation network, connected to road sensors, predictive analytics systems, public transit and more. This could inform a commuter’s decision on what route to take or what the best connection would be to make given what train or bus will arrive next. In a traffic command center, Watson could help transit operations ask “am I missing something?” Outside factors – like a sporting event, a parade or a demonstration – can also impact what decisions are made to manage traffic, but often aren’t known far in advance and might not be in the models typically used. Operators could query how these might affect their different options like signal or speed limit changes, lane closures or the effect of metering and dynamic pricing in correlation with the data they are already tracking. This additional information could help them make more informed decisions on how to avoid congestion. Could we better connect public transit with air travel, railroads, cars, etc. for a more seamless journey? Perhaps a Watson-like system could help us sort through and then refine what the best option might be when faced with a multitude of options for transit modes, a variety of connections, the different scenarios involving departure and arrival time and a variety of other criteria. The possibilities are endless. It will be exciting to see what comes next no matter who ends up in the Winner’s Circle. Gerry Mooney is the general manager, Global Government & Education, at IBM.