An ETA, or estimated time of arrival, is a term used widely in transportation predicting when a means of transport, or freight shipment, will arrive at its destination. In the world of logistics and supply chain management, obtaining an ETA for a shipment in transit has a wide range of benefits. Sharing ETAs with end-customers helps manage their expectations while operational teams can use this information to help ensure deliveries are on-time, helping manufacturers avoid production line halts or retailers avoid stocks outs, for example.
An ETA refers to the arrival of a means of transportation on site, whether it's for loading a shipment or unloading a delivery. An ETD often refers to two different things. It can mean ‘estimated time of delivery’ of a shipment to a consignee. It is also commonly used to mean ‘estimated time of departure’.
Calculating an ETA for road transportation is more complex when compared to some other modes of transportation, since the nature of roads introduces many more uncertainties compared to rail and air travel for example. Roads are shared with many other vehicles, producing traffic and increasing the likelihood of accidents which can cause delays.
Although currents and winds affect ETAs for ocean cargo, a lot of delays happen at the port terminal rather than en route, as shipments can become held up by customs or delayed processing due to weather, vessel malfunctions, lack of berths or technical faults at the port itself.
Giving advance notice of delays allows for proactive measures to be taken, mitigating negative customer impacts, in turn producing higher levels of customer satisfaction. However to make ETAs accurate and reliable, they need to be constantly updated based on real-time location data. Real-time ETAs unlock greater value from a supply chain, shifting its capabilities from ‘proactive’ to ‘predictive’.
Knowing accurate ETAs can reduce administration costs for organizations by automating processes and allowing teams to focus on exceptions. This allows shippers to better utilize teams who used to perform time-consuming tasks like sending delivery notifications, calling carriers to follow up on the whereabouts of deliveries, scheduling of docks and processing of payments through workflows.
In turn, this can increase productivity of customer service teams, as well as operations teams at warehouses and distribution centers. It allows these teams to make changes to dock scheduling on the fly, optimizing the labour at cross-docks by receiving proactive ETAs.
Real-time ETAs also help shippers gain greater transparency of carrier operations. This transparency helps to ensure costs associated with freight are fair and reasonable, particularly for unanticipated costs through workflows.
Consequently, carriers benefit from advance notice of a shipment’s change in status, helping to reduce dwell-times, wait-times and penalties, allowing them to more easily adapt their operations to better utilize their fleet and resources.
In road transportation visibility solutions, GPS position accuracy is critical. The status of a shipment or delivery is automatically determined based on the position of trucks (telematics systems) in relation to key sites. These sites can include factories, warehouses, distribution centers, cross-docks, retail outlets, etc. Each of these sites is surrounded by a ‘geo-fence’, which represents the site’s immediate surroundings. As soon as a truck’s GPS reports a location within a ‘geo-fenced’ area, it triggers an automatic notification in real-time to update the status of the shipment. For example, ‘arrived on site’ or ‘left the site’. In addition, if the GPS signal is not cleansed, it’s difficult to determine whether the driver is idle or driving, and at what approximate speed, which directly impacts ETA accuracy.
A basic ETA can be calculated very simply, by knowing how far a shipment needs to travel and the speed of the vehicle carrying that shipment. Routing APIs, used in common consumer map and navigation apps, are sufficient for basic tracking, taking into account things like live traffic information, roadworks, accidents and time of day. However, for freight transportation, the ETAs produced by such apps are not accurate enough. They do not take into consideration the driver stop time requirements and assume continuous drive from A to Z. For this reason, results are usually very poor, with ETAs predicted 24 hours prior to arrival usually off by 16 hours on average.
This graph shows the mean absolute error (the average magnitude of errors in a set of predictions) of a routing API versus an algorithm leveraging machine learning when calculating an ETA. The inaccuracy of the routing API steadily increases the further ahead it is made for a planned delivery.
An ETA calculation aided by machine learning on the other hand achieves a mean absolute error of around 2 hours, even when calculated 24 hours ahead of a planned delivery.
Theoretically, there are an infinite number of real-world variables that can impact an ETA. From the type of vehicle, to traffic, weather conditions, the size and weight of the load, driving regulations and many more. Understanding which ones are important, sourcing relevant data and then making sense of this data requires both expertise and powerful technology.
Shippeo has a dedicated team of data scientists and engineers in-house. Using machine learning and by sourcing over 200 data parameters, we’ve developed a proprietary algorithm that allows a market-leading degree of ETA accuracy and reliability to be achieved.
If you’re interested in finding out more about how Shippeo’s market-leading ETA accuracy could help your organization streamline transport operations, don’t hesitate to download our white paper 'The business value of accurate and reliable ETAs'.
Consultez notre Politique de Confidentialité pour plus de détails sur l'utilisation et le stockage de vos données personnelles.