Distribution Innovation (DI) is part of the Schibsted family* and is the leading Nordic logistics and subscription technology service provider. With more than 2.2 million products going through its system every day, DI is working with billion-dollar companies and local publishers alike. Simply put, DI manages the entire value chain from order to delivery into the hands of the consumer. While the company is still unknown to many, DI serves 2.5 million households in Norway, 3.8m in Sweden and 1.2m in Finland.
ML Optimizes newspaper delivery
As millions of packages and papers are to be distributed through the systems on a routine basis, planning, prediction and optimization are all vital. Solving such tasks are often described as the perfect job for AI, and the successful implementation of AI across the DI value chain indicates a belief in that very idea. So what’s the key to DI’s work with AI?
“If you ask me, we have been very good at applying these new technologies in ways that make sense for both people and the planet”, says Frode Finnes Larsen, CTO at DI.
So what makes sense for the planet? One idea could be to not waste our world’s resources on newspapers that won’t be read. To explain how DI works to do this, let’s look at an example where AI, or in this specific case, Machine Learning (ML) is used to optimize newspaper deliver.
Every day newspapers are sent from DI’s distribution centres to various retailers such as Seveneleven or Narvesen. If there are unsold papers at the end of the day, they are sent back to the central and the retailers get a refund for the returned copies. A key challenge for DI here is to make sure that the right amount of papers go to each store every day. Enter stage, ML!
Through an ML solution that predicts how many papers a specific store will sell during a given day, the DI system informs not only the distribution (i.e. how many papers are sent to each store) but also the printing of newspapers.
Identifing the most efficient route
Another example of AI put to use for environmental good is that of DI’s route optimization tool. Last mile delivery, or put differently, being able to deliver papers and packages to people’s doorstep is another key aspect of the DI service. Every day, delivery employees are assigned to various routes with delivery points along the road. Regardless of whether the delivery employee is driving a truck, riding a bike or walking, the DI system uses an AI system trained on geographical- and address data in order to optimize the route and ensure that the most efficient path is taken. This AI-powered planning tool is particularly important for the delivery routes of cars and trucks, as the optimal route will minimize fuel use and reduce co2 emissions.
“The beauty of our model is that it focuses only on the delivery point. It does not care about the name on the door,” says Frode Finnes Larsen, highlighting the fact that the AI solution does not discriminate by for example prioritizing clients or neighborhoods, but seeks to generate the optimal route in order to save resources.
Using digital tools across delivery systems may seem like a given today, but the fact is that many otherwise highly digitalized markets still use analogue solutions like paper slips and log books for deliveries. DI has been employing digital solutions since its start back in 2001 and has no plans on stopping.
“Employing digital technologies is embedded in our DNA,” says CTO Frode Finnes Larsen.
Innovation is core business at DI. As history has shown, the distribution company is keen to employ new technologies and tools across the business to make life easier for customers and employees alike. As noted by Muhammed Sadjit, who has been working at the distribution centre in Nydalen, new technologies continuously help employees do their jobs better and faster.
“That makes me happy,” says Muhammed.
While DI has an ambition to further explore AI and its potential, many tasks along the value chain still require the very unique skill set of human beings. One such task is found in what is internally known as “the brainy station” at the distribution terminal in Oslo’s Nydalen. At the brainy station, Employees manually investigate faulty packages or parcels that have not been able to get delivered.
Here, data and insight tools are used as support for a task requiring human expertise. According to Jovana Vrcelj, a distribution employee at the Nydalen terminal, the work done at the brainy station is based on the skill of understanding irregular mistakes. By reflecting on human made errors like for example misspelled addresses or poor handwriting, Jovana and her colleagues step in to make sure that every parcel finds its rightful destination. She describes the work as similar to that of a detective sorting through clues.
“Humans make the best detectives,” says Jovana and digs into another mystery.
* Schibsted owns Distribution Innovation together with Amedia
Read more about DI in Schibsted Future Report 2020