Posti uses AI to improve parcel routing efficiency

LinkedIn +

Finnish postal operator Posti is to begin using a dynamic, AI-driven parcel routing system that can anticipate parcel lockers’ available capacity with an accuracy of 96%.

Some parcels aren’t picked up by customers in time – this leads to hundreds of parcel lockers becoming completely full every day and posts having to leave parcels in empty lockers that may be further from their intended customers. This may also result in customers having to wait longer or drive further before they can receive their parcel.

Such situations occur because the filling rate forecast for parcel lockers used to be based on a fixed average that did not take into account variation according to the parcel locker, day or season. The filling of parcel lockers is also limited by both the number and size of individual lockers. While small parcels can be put in lockers of various sizes, larger parcels will only fit into some of the lockers, meaning this size consideration needs to be factored in.

Posti’s dynamic parcel routing system will predict how many of the parcels in the parcel locker will be picked up within 24 hours, before the driver brings the next load of parcels. With this information, delivery drivers can reserve the correct number of items for the next day and reduce the amount of driving needed to deliver parcels. Therefore, the prediction tool uses more accurate capacity forecasts to make the delivery process faster and ensure recipients get their parcels as soon as possible.

Currently, Posti is working on creating an advance message system to further improve delivery efficiency. Before the parcel arrives at Posti, the online store will send an advance message about it. The sending time of the message will vary by store. Artificial intelligence will be used to predict when the parcel will actually arrive in sorting. If the arrival time can be accurately predicted, advance bookings can be made for parcel lockers. In the future, artificial intelligence and machine learning will predict changes to the filling rate of Posti parcel lockers. With a prediction model capable of learning, parcels can be delivered without unnecessary driving and to a location near the consumer.

Jari Paasikivi, the project manager responsible for the parcel routing system at Posti, said, “Popular parcel lockers cannot be expanded if they are located in a limited space, such as inside a store. With artificial intelligence and machine learning, we are able to get a more accurate forecast of parcel locker capacity, which helps us route parcels to the parcel lockers chosen by recipients more often.

“In addition, more parcels can be made to fit into certain parcel lockers. The parcel can be delivered to a location as near to the customer as possible, which reduces unnecessary driving and the emissions from it. We already know with an accuracy of nearly 100% which of the parcel locker’s individual lockers will be emptied and are able to reserve the correct number of items for the next day.”

Riku Tapper, who is responsible for Posti’s data and automation, said, “We have been building our ability to use data for a wide range of purposes with a long-term view. Having artificial intelligence as part of our parcel locker network is an excellent example of how data and technology can be used to improve the customer experience. We have particularly invested in our machine learning competence, and the artificial intelligence that routes parcels has been developed fully by our own staff.”

Share this story:

About Author

mm
, web editor

As the latest addition to the UKi Media & Events team, Elizabeth brings research skills from her English degree to her keen interest in the meteorological and transportation industries. Having taken the lead in student and startup publications, she has gained experience in editing online and print titles on a wide variety of topics. In her current role as Editorial Assistant, Elizabeth will create new and topical content on the pioneering technologies in transportation, logistics and meteorology.

Comments are closed.