Online supermarket Picnic is revolutionizing the online food shopping sector in the Netherlands and beyond. They are celebrating their fifth year in business. Picnic delivers e-groceries to thousands of customers every day. To do so both efficiently and effectively, the Picnic’s distribution system needs to be as smooth as possible.
Picnic engineer Regan Koopmans reflects on the computational logistics of online food deliveries: “Logistics is the science of efficiently moving items from one place to another. This sounds simple at first, but it serves as the gateway to some of the most exciting frontiers in mathematics and computer science. The world of logistics is fundamentally one of algorithms and optimization. It is, therefore, no surprise that algorithmic thinking is so deeply integrated into the culture of engineering at Picnic”.
Advanced Analytics & Algorithms Team
In his blog Regan illustrates this by highlighting some of the most interesting problems that Picnic is solving, and why a career in logistics should be on your radar. The market is currently in a renaissance of machine learning. Many of the recent improvements in machine learning have found applications within Picnic. They have an entire team dedicated to actively exploring learning-based solutions to promote business interests; Advanced Analytics & Algorithms Team.
Delivery network
One part of the Picnic system is the vehicle routing model, which determines which routes are optimal given the customers and their placed orders, amongst other factors. An important input into this model is the drop time: how much time they expect delivery to take for a given customer. A recent Picnic-blog covers why drop times are so important and how they, the Data Science team within Picnic, developed a model to better predict this amount of time.
Demand forecasting
One important application is the prediction of demand. Using neural networks Picnic is able to make reasonable estimations about what demand an item might have on a given day. The models used for such predictions draw on features such as previous demand, weather, and the occurrence of public holidays. This allows preemptive stock keeping and minimizes the regional unavailability of items.
Challenges
On Twitter, Daniel Gebler, Picnic CTO, sees as challenges to tackle: the need for a large amount of data, the need for perfectly clean data, and the fact that it is hard to generalize and explain the results of computational logistics.
Academic rigor
As Regan Koopmans sees it: “the number of businesses doing truly novel things in software is extremely small. Logistics is one of the industries that demand academic rigor and allows developers to experience the algorithms that they might have studied in university. Working at Picnic is interesting in this way, and that is the highest praise I can give it”.