By Pankaj Sachdeva, Vice President, Innovation and India Site Leader at Pitney Bowes
The global pandemic has accelerated digital transformation in many industries by several years and many of these changes are here to stay. Just think about how you accessed verticals such as Education, Financial Services, Retail before the pandemic and how you do it now. Companies have sped up their customer and supply chain communications and the rise of digital channels for client interaction has led to the collection of multi-folds of data that can bring out valuable client insights. The logistics vertical – Transportation, Shipping, Supply Chain, Warehousing – is no different.
Big data analytics with IoT and AI/ML are helping organizations across logistics, transportation, cargo, shipping, warehousing improve visibility of their businesses, add revenue streams, improve employee safety, and enhance customer experience. Below are some examples:
1. Improve visibility and operational efficiency
o Predict volumes for better planning of number of passengers, cargo, shipments, packages. Based on historic data and pattern analysis such as on seasons and cycles, big data analytics helps forecast volumes into the future. Having a view of incoming and outgoing volumes enable business forecasting and better planning of infrastructure and resources, both human and machine.
o Facility management / Warehouse management –In addition to predictive maintenance of different assets, robotic automation is being used in facilities and warehouses for package segregation based of pin codes, picking, packing and is helping companies improve efficiency.
o Freight movement & Routing – Real time data analytics on weather, traffic, accident, allows route optimization of vehicles and freight for faster deliveries.
o Minimize fuel spend & reduce environmental impact – Other than route optimization for minimum fuel usage, companies are ensuring the transportation vehicles – trucks, vans, ships – are efficient and are used resourcefully. A leading tyre company is offering a service to trucking companies where they would fit sensors in tyres and analyse driver acceleration, braking, turning patterns.
2. Add Revenue Opportunities
o Personalized experiences – Big data accelerates revenue growth through client segmentation and targeted marketing for client acquisition, cross selling, and retention. Say,an organization’s data model predicts‘Same Day Delivery’ shipments will be in great demand in an area, but the organization doesn’t have enough resources planned, the organization might as well start giving discounts on 3-4 day delivery for clients to entice and retain clients.
o Create differentiated products – Data is a big differentiator for products. Analysis of data can help add features or improve the usability of your products. For example, offering delivery timeline predictions through big data analysis. Similarly, analysing the drop rate at junction in the usage journey by a particular segment of clients can help understand and resolve the issue.
o Add new revenue streams – Offering analytics to clients is a big revenue stream. Offering end-to-end package visibility, return prediction and management, are others which are led by big data. Additionally, consulting services to help save clients shipping and logistics cost added services revenue.
3. Enhance Customer Experience and Services
o Understanding your clients – Knowing your clients’ needs and preferences is key. Data collected through multiple client-product interactions help build statistical models that can accurately predict client actions.
o Solving client issues –Usage data also helps predict potential client concerns – issues with product usage, workflow concerns for clients, and enables organization to provide resolutions beforehand. Such initiatives are helping improve customer satisfaction scores.
While there are other use cases of Big Data in Transportation, it is not about the breadth of analysis, but the depth of analysis. The two basic requirements for good data analysis are data volumes and data quality. An organization must be able to capture hundreds of thousands of events and ensure quality each time for accurate predictions. It is also essential to have the capability to stream analytics and real time analysis, especially for time sensitive use cases. While AI/ML application on data helps automation and provides timely availability of the analysis, it is critical for organizations to action the analysis timely to unlock the real value of data in transportation.
