STOCK OPTIMIZATION ANALYSIS FOR KRAMP

Kramp is a solid and reliable spare parts supplier for many businesses throughout Europe. With more than half a million items in their assortment, they supply companies in the agricultural industry with the necessary parts for the smooth operation of their clients’ products.

With warehouses throughout Europe and thousands of customers and suppliers, logistics is always a hot topic for them. How to supply the right product to the right company at the right time? In 2017, Anchormen and Kramp started working together with the goal to optimize this process through the use of data.

After an initial data analysis and several workshops, we defined three primary areas of interest, which were causing disruptions in their operations. The goal was to reduce the risk of stockouts as much as possible by optimizing each of these areas.

We looked at the issue through the lenses of supply and demand. On the demand side, Kramp is using inventory management software to place incoming orders which also has a forecasting algorithm on top of it that serves as a planning tool. It became clear that there are some limitations both in the inventory management and in the forecasting methodology. That quickly became a main area of focus which had to be improved by revising buffer stock sizes, deep diving into seasonal sales patterns, etc.

On the supply side, two main obstacles were identified, which when solved will greatly improve Kramp’s response times and stock levels. Firstly, container shipments with long lead times were identified as a cause of preventable stockouts. And secondly, it was observed that manual purchase order handling was not always prioritized most efficiently and hence was not consistently within the desired response time. By designating alternative short-term suppliers and creating daily overviews for the business these critical points will be kept in check from now on.

Insight into the company’s data allowed us to consult Kramp on the best ways to reduce stock shortages. In the end, they managed to improve their response time, reduce unnecessary stock, and successfully activate their data.