+33 1 85 76 20 29
contact@citodi.fr

Citodi Approach

The CITODI approach: Responsive and self-learning Event algorithms for real time

During the long R&D process we have followed, we have developed our own algorithms, and we have designed them in such a way that they can handle any touring problem with the highest degree of dynamicity.

In addition to the so-called “static” optimization that we achieve with the best in terms of performance, our “dynamic” algorithms are natively “Event Responsive”, i.e. their structure and operation allow them to continuously calculate tours while listening to the feedback from the field.

Any event (a new delivery order to be integrated, an absent customer, a customer who wants to postpone his delivery slot, a traffic evolution, a driver who breaks down with packages in the trunk, etc.) triggers an algorithmic calculation that instantly and optimally modifies the current routes to avoid interrupting the service.

To do this, we have integrated and adapted the algorithms proposed in the literature, which we have greatly improved and made more complex to take into account the realities on the ground.
In addition, we implement Machine Learning strategies to make our algorithms self-learning, for example:

– If a junior driver is slower than an experienced driver, we adapt his journey times so as not to impose a pace that he cannot yet maintain.
– We anticipate the likelihood of new delivery orders being issued to reposition the driver fleet when they have nothing to do (e.g. for meal deliveries)
– If the operating time on a point has been x minutes for several weeks while the average time is y minutes, we adapt the operating time to be more precise on predictive optimization.

Our objective is to offer our customers the most efficient algorithms possible, making their daily use as easy as possible. We are constantly concerned with real-time optimization without service interruption, in order to transform the optimization of static tours that are too rigid into a flexible and scalable dynamic optimization.

Our ambition: to simplify your life in the field by providing you with the power of mathematics.