Harnessing Big Data
for smarter transport and logistics

Harnessing Big Data for smarter transport and logistics

Often, the logistics and transport sector is quick to adopt new technologies, as was the case with RFID and GPS. These sectors are currently finding creative applications for new technologies such as the Internet of Things, Artificial Intelligence and driverless vehicles. The ongoing digital transformation of transport and logistics has resulted in the creation of huge amounts of data, from detailed shipment and delivery data to routing and GPS information. This ‘big data’, collected from a variety of networks and platforms, can be analysed in order to develop new business models, achieve operational improvements and improve customer experience1. This will allow logistics and transport companies to remain relevant and competitive.  

Operational improvements

In just about any field of industry, smart application of learnings based on big data will improve performance and resource planning, as well as prediction accuracy, and support strategy development. One important aspect of the logistics and transport business is route optimisation. In logistics, maximising efficiency in the ‘last mile’ of delivery routes is essential. By looking for patterns in vehicle routes and traffic conditions, the best choices can be made at different times. This saves time, whilst also optimising the use of assets and resources.

In the past, route planning was often based on historical, anecdotal or third-party data. The presence of layered, up-to-date information fully supports the ongoing optimisation of routes. Routing optimisation can now take driving behaviour, road conditions, weather and other factors into account. Drivers can even make use of crowd-sourced data on traffic and road conditions to improve routes in real time.

Anticipatory logistics can make it possible to improve process efficiency by anticipating demand. Predictive analytics can help reduce downtime for vehicles. Siemens, for example, is introducing data-driven predictive train fleet maintenance. In-transit stock can be monitored and departure and arrival times can be communicated thanks to management analytics. What’s more, big data can help reduce fuel consumption and sensors can help optimise fuel input by monitoring vehicle engines.

Leading logistics companies are already working with big data-based applications. Uber, for example, recently launched its ‘Uber Freight’ platform, which connects drivers to available shipments, similar to its taxi app. Major logistics firm Geodis recently launched the ‘Neptune’ platform, based on real-time transport, reporting, KPI analysis and document archiving. This allows customers and hauliers to easily and quickly manage all activities from a single platform.

New business models

Every fleet of vehicles is continuously covering vast distances and a variety of terrains. Data collected using sensors, cameras and other measurement equipment can be provided to various types of customers. A vast range of information from noise levels and pollution to traffic density may be of interest to everyone from city planners and policymakers to academic researchers.

Big data can also support the integration of logistics into other areas of business, for example, merging IT, the Internet of Things and Artificial Intelligence to optimise the role of logistics providers in Industry 4.0 and Smart Factory developments. Theoretically, third parties could offer services that improve end-to-end visibility across supply chains and related sub-processes.

Business models using vast volumes of data can also be adapted to meet the requirements of especially demanding customers in certain areas or could be simplified to provide a lower-cost service where appropriate. Another unique option made available by data and connectivity is crowd-based pickup and delivery. Carriers planning to follow a specific route can check whether packages need to be picked up or delivered along their routes.

Traditionally, logistics providers have picked up pre-manufactured products from warehouses and factories, but data means this role could change: logistics providers could act as data hubs and manufacturers with their own printing machines. They could offer end users product designs or options for developing their own designs, print these on demand and deliver the finished items. At present, UPS is already offering 3D CAD and 3D scanning services at over 50 UPS store locations.

Passenger transport companies can develop end-to-end trajectories to bring about greater convenience for travellers. For example, some airlines are already offering pickup services connected to flights, ensuring passengers get to the airport on time. Furthermore, train, bus and ferry operators are starting to advise on optimal routes across different modes of transport, allowing travellers to get from ‘A’ to ‘B’ faster and more easily on a single ticket.

Customer experience

Customer insights gained from different types of data collected in the transport and distribution network help companies make the right decisions to adapt to customer needs.

They can also accurately gauge satisfaction and avoid customer churn by taking adequate and timely counter-measures. This data information can be collected through web-based interactions, sales channels, and by applying analytics techniques to social media analysis. Based on patterns found by analysing data, companies can anticipate demand and optimise planning and operations. For example, they could find search trends in specific regions.

Taking a data-centric approach to public transport allows planners to find better transit routes, and dynamically adapt transit to the ever-changing and fluctuating patterns of demand. This also opens up the possibility for multimodal mobility planning: digitisation and system integration at multiple levels enables a seamless combination of different types of transportation in a single journey, including related information and planning services.

Customers can quickly and easily find out the most efficient and appropriate form of transport at any time, thanks to data collection and analysis. Information on waiting times, seat availability, disturbances en route, etc. can all be taken into account. However, this requires the correct infrastructure to be in place, supported by high-quality, real-time information systems that enable the connection of routes, schedules and fares.

This approach makes travel much easier for individuals, who could move between modes of transport with a single ticket. It also helps to significantly reduce congestion and power consumption. Customers may start using routes or vehicles they were previously unaware of and can be continuously provided with up-to-date information, even across different devices.

Challenges

The vast quantities of data to be analysed require significant storage and processing capacity and possibly a rethinking of data architecture, including both off-the-shelf and tailor-made analysis tools.

There are some significant privacy and security issues related to storing and mining vast amounts of (anonymised) data that need to be taken into account. Another challenge comes for self-driving vehicles. Self-driving vehicles have the ability to revolutionise transport and logistics, but legislation and infrastructure will need to keep up and support these developments.

‘Big data in the digital age and how it can benefit public transport users’, published in the journal Research in Transportation Economics concludes that cities worldwide are enthusiastic about mobility platforms using big data to predict current and future vehicle and passenger flows, to improve accessibility, liveability and sustainability. However, a study of 10 mobility platforms, as well as pilot projects, concluded that the more ambitious a mobility platform is, the more governance challenges arise. A higher level of technical ambition leads to more misalignment with existing institutions, claims the study, particularly if this higher level of ambition requires using more personal data as privacy regulations will need to be taken into account.

Any barriers to making the most of big data in transport and logistics are more likely to be regulatory than technical. Big data can have a highly positive impact on the logistics and transportation industries, creating new business opportunities and improving both operations and customer experience.