By 2020, it is estimated that more than 40 ZB of data will be generated annually. This “Big Data” is transforming every single industry. In this blog, I will talk about how Big Data is transforming Public Transportation, especially Rail Transportation.
Big Data is transforming both the Plan phase and Operations phase of the Rail transportation. City authorities who are in-charge of this transportation service, should consider leveraging Big Data for 4 key use cases:
Big Data Use Cases in Plan and Operations Phases
1. Planning and Demand Modeling
With Big Data, authorities can generate more precise understanding of the customer demand on different routes. They can map customer journeys across multiple modes of transportation – trains, buses, private modes of transportation etc. They can use all this data to improve planning on the future train routes, frequency on existing train routes and size of trains.
This will help reduce customer wait times and walk times resulting in increased ridership on the trains.
Authorities can also optimally plan for additional services such as retail stores on the routes through better understanding of customer journey maps. E.g., open food outlets at locations where large number of commuters walk through during times of breakfast, lunch or dinner.
2. Predictive Maintenance
By leveraging Big Data, authorities can predict optimal maintenance requirements of the equipment – trains and tracks. With Big Data, data from the sensors installed on the equipment can be analyzed at much faster rate and at more minute-level. This can be used to predict upcoming faults at the individual component levels such as brakes, a stretch of rails etc. With this, authorities can schedule maintenance of the equipment precisely at the right time – which is not too early (which is unnecessary and expensive) or not too late (which is expensive and disruptive to the service).
One of our clients in the public transportation space has successfully deployed Big Data for scheduling maintenance of the equipment and the results are staggering – Mean time to failure of the equipment reduced by almost 80-90% and equipment life increased by 200%. This further improved customer safety and satisfaction, enhanced equipment utilization and reduced operating costs.
3. Event Response
With Big Data, authorities can have an intimate understanding of customer journeys – start and end points involving trains, buses and even private modes of transportations. This helps authorities answer the following questions, and thereby, better equip them for both planned and unplanned event.
- Which customer will be impacted?
- Where should we deploy alternate means of transportation?
- How much additional capacity should be added?
- And, what is the best way to reach customers? Facebook, Twitter, Text Messages?
It is very important to have fast and optimal response especially during unplanned events and Big Data technologies today provide tools to achieve such as response.
4. Personalized Services
With the intimate understanding of a customer, authorities can tailor communication to each rider via preferred communication channel (Email, Text, Phone etc.). These personalized messages can include:
- Changes in the service on individual route(s) that a customer cares for
- Looming weather-related events that might impact service
- Upcoming events (E.g., sports games) and their impact on the service
- Targeted advertising (E.g., food coupon for a restaurant along the route)
Instead of spam of messages that customers get these days, this level of personalization is something customers can appreciate and depend on. It improves customer satisfaction and helps increase the ridership of trains while providing authorities new revenue sources such as targeted advertising.
Where to Start?
Predictive Maintenance is certainly the first use case that authorities should leverage – data is generally available from sensors on the equipment and the use case is proven at multiple organizations to provide quick and tangible cost savings. After that, authorities should look into improved planning and demand modeling and better responses to an event.