Knowledge

How AI and machine learning are shaping the planning board of the future

Transport has changed over the years. The sector has grown and transport companies are also gathering more and more data. What they do with that data is another matter. How can we process it and do something useful with it? That is why the DALI programme was set up (Data Science for Logistics Innovation): what opportunities are there and how can we use them in the transport world? We have a clear vision about that: we want to use that data to proactively inform our customers' planners about discrepancies during trips so that they in turn can take appropriate action.

DALI: Data Science for Logistics Innovation

The DALI programme was set up to identify and utilize opportunities in data science for SMEs in the logistics sector in Brabant. Those opportunities cover three themes: strategic insights (one size doesn’t fit all – the strategic choices that we have to make to add value for customers), demand forecasting (data analysis to get a clearer picture of future demand) and planning (how to deploy people, resources and stocks even better to make our operations more efficient and greener). The DALI programme fits in beautifully with the mission of NextUp, making the transport world a bit more efficient.

The planning board of the future

TMS systems are still often too much about recording information, with the planners making decisions that are based on incomplete and incorrect information. We are going to develop a self-teaching component in NextUp to tackle that using AI and machine learning, based on the data we collect. We are doing this together with our partner (and customer) Jan de Rijk. Assisted by NextUp, Jan de Rijk delivers supplies day and night for hundreds of customers. The planners collaborate very closely to achieve this. And their biggest challenge? Communicating quickly when things don’t go entirely to plan: the driver left a bit late, a package wasn't scanned and has been lost, the client was not at home – all kinds of things that are outside the planner's control, but essential for the process.

What if we were able to detect all those irregularities in the logistical process and inform the planners about them proactively? More than that, even: what if we were able to magically turn those discrepancies into planning decisions and present them proactively to the planner?

Soon, machine learning and AI will let us communicate better and proactively about irregularities and planning decisions, which will make the logistical process quite a bit more efficient:

Fewer mistakes made
Action taken more quickly
The risk of human error reduced

How will we achieve this?

The DALI programme is now in the pilot phase, in which we will be tackling specific case studies drawing on a range of disciplines and professionals. We will be collecting data, processing and analysing it and then applying it in practice. Together with these professionals, we aim to develop tools that will take the logistical process to the next level.