Supplier scouting has always been a strategic activity, even before the latest crises experienced, as companies need to gather information on potential suppliers, evaluate their offers, and select the best business partner. In the current volatile and uncertain environment, companies are reshaping the way they manage their supply chain by enhancing their current supply base through active scouting of new suppliers.
Supplier ranking: how can Artificial Intelligence help us
In the Food & Beverage industry, supplier scouting is a delicate aspect to manage as their performance must meet fundamental requirements, fulfilling specific criteria such as timeliness, quality, sustainability, etc. Therefore, enhancing the scouting is crucial and requires the development of new digital models and tools for data collection and analysis. In this context, artificial intelligence (AI) enables companies to improve scouting through the automation of tasks and the predictive power of machine learning algorithms, thus performing increasingly accurate assessments.
Supplier performance are calculated through the implementation of AI and ML algorithms, with respect to the specific conditions under which they were processed to provide a precise ranking. Therefore, given a specific situation, AI and ML algorithms, allow to estimate which supplier is most likely to deliver the required performance in line with one or more dimensions of analysis, such as quality and punctuality, quality and sustainability, etc.
sedApta and AI algorithms
The algorithms implemented by sedApta, allow to manage supplier scouting in two different ways: reactive and proactive.
In management systems, such as SAP, averages of non-vertical supplier evaluations are calculated by dimension of analysis. With the introduction of ML algorithms, all this information is contextualized-expected delivery date, actual delivery date, etc.-by analysis detail such as time of the year, order quantity, order type (product type), etc.
All of these details are submitted to ML algorithms, which, once processed, proactively return as output the list of suppliers by dimension of analysis. For example, if a given product is considered, at the top of the “ranking” of suppliers we will find the one with higher ranking, that is the most likely supplier, to meet the required performance.
Moreover, since companies in the Food & Beverage industry have to deal with fresh and expiring products, and also need to manage the process in a fast way, AI supports them in the event they have to change supplier to deliver goods in the expected time and in a reactive way. For example, if we consider the time aspect, the supplier who is in charge of the shipment notifies that the shipment will be delivered late. Therefore, support will be requested to the virtual assistant – in the specific case of the algorithms implemented by sedApta, it will be Miss Elisa – in order to find an alternative supplier out of those in the list, who is most likely to meet the goods’ expected delivery date.