Fleet operators across the UK are facing mounting pressure. Whether it be through rising customer expectations, tight delivery windows or ongoing sustainability targets, traditional planning methods are struggling to keep pace.
Given these circumstances, machine learning has fast become a vital component of modern fleet and logistics management. To emphasise its importance, in 2023, themachine learning in logistics market size was valued at USD 2.8 billion. And is now estimated to register a CAGR of over 23% between 2024 and 2032. Beyond these numbers, Andrew Tavener, Head of Marketing, Descartes, believes machine learning is a great competitive advantage and enables fleets to turn everyday delivery data into intelligence that continuously improves planning accuracy, driver performance, and customer satisfaction…
The science behind machine learning
At its core, machine learning algorithms are mathematical models based on sample data in order to make predictions or decisions without being explicitly programmed to do so. The information generated by GPS-tracked fleets is an excellent data source for machine learning to improve delivery performance. By learning from real-world outcomes, machine learning helps fleets move from relying on assumptions to operating with precision. The result? Greater reliability, better use of vehicles and drivers, and a stronger delivery experience for customers. Here are six areas where machine learning is transforming delivery performance today:
- Improving delivery location accuracy
One of the biggest challenges facing businesses that deliver to construction sites is the unpredictable and changing site conditions. For instance, being able to determine the delivery location at green field construction sites. This is because sites don’t often have established road systems in place, or the addresses don’t correctly reflect the actual delivery point. On top of this, some companies at the beginning of a job may not have the digital map data in their databases yet because the location is so new.
Machine learning can use the actual delivery location data to refine the address or geocoordinates used by the route planning system. This results in a more accurate and feasible route, precise planned delivery times and less confusion for the driver as they know exactly where to make the delivery.
- Refining service times
Service times can be influenced by a number of factors, whether it be the resources involved, the company’s vehicle type, or the products being delivered. Many route planning systems have the ability to model service time based on the factors above using concepts like ‘engineered standards. While these can be highly developed models, they’re still representations of the real world and may not consider all of the factors that drive service times. Machine learning can take actual service time data to determine the most representative service time. Allowing for more accurate scheduling improves on-time performance and can free up additional time for more stops within a route.
- Calculating representative stop times
Stop times can vary based on the customer location, parking restrictions, and other physical considerations (including vehicle type and driver skills). Again, many route planning systems have the ability to model stop times in detail, but they are still representations or all of the information about an individual stop is not available to be considered in the calculation. Machine learning can take the stop time data to determine the most representative stop time. The result is more accurate stop times, enhancing not only delivery reliability but delivery productivity too.
- Predicting travel times with greater accuracy
Even the best mapping data cannot account for every real-world factor that affects journey times. Traffic flow, weather and vehicle type all play a part. Whilst most of these can be modelled, particularly in the case of road data, in a very detailed fashion, local conditions mean road speeds can vary greatly. Machine learning can use delivery data to determine if modelled road speeds are slower or faster than what is actually experienced. This information can be used in route planning to create more accurate and reliable routes.
- Understanding driver performance
Driver behaviour has a significant influence on delivery performance. Aspects such as experience, driving style and consistency all play a role. Therefore, understanding driver performance allows for a better definition of what constitutes ‘good’ performance as well as correctly incorporating it into route planning and execution processes. Machine learning helps evaluate driver performance to determine a performance factor for each driver to help maximise delivery productivity and correctly reflect driver capability.
- Providing more accurate ETAs
Accurate ETAs are crucial to customer satisfaction. Younger contractors especially are used to an ‘Amazon’ style delivery process, where things are delivered where and when they are promised. So, when delivery windows are unreliable, contractors lose time and customers lose confidence. Machine learning combines all the insights above, from accurate delivery locations to realistic service and travel times, to calculate more precise ETAs. With these improvements, fleet managers can provide customers with reliable updates and identify potential delays before they cause problems.
To conclude
Machine learning allows businesses the opportunity to turn everyday operational data into meaningful intelligence. Fleet operators already have the information they need to do this; they just need to use it!
By embracing machine learning, businesses can plan and execute deliveries based on real-world experience rather than assumptions, which will have an undeniable impact on their business which is immediate and measurable. Not only can they expect to achieve more accurate delivery plans, better use of fleet capacity, and an improved on-time performance, but they will also benefit from higher customer satisfaction. In an industry where every minute, mile, and message counts, it is a great competitive advantage.
