Use AI to improve Supply Chain inventory performance
Share on email
Share on twitter
Share on linkedin
Share on email
Share on twitter
Share on linkedin

Use AI to improve your Supply Chain inventory performance

Alis Hinrichsen
Alis Sindbjerg
Hinrichsen
Thought Leader & Strategic Advisor

Effective inventory management is one of the single biggest actions a company can take to maximize its competitiveness. It simply ensures that resources are being used smartly. In this blog post, we will look into how you can utilize AI to improve your Supply Chain inventory performance by optimizing your assortment.

Effective inventory management is one of the single biggest actions a company can take to maximize its competitiveness. It simply ensures that resources are being used smartly. That being said, a new report published by Optilon shows that many companies have a blind spot when it comes to inventory management. 22 percent of the inventory is redundant for a Swedish average company. This could be the case for many companies in the Nordics.

It’s not just about having fewer goods in stock. By always having the right mix of goods, missed sales are greatly reduced, while taking up less storage space and reducing the risk of an item being outdated. Having the right mix assures smart use of resources, but what is the effect of also understanding how you should manage your assortment? In this blog text we will look into how you can utilize AI to manage the product portfolio and increase your sales

Why is the right assortment important?
Effective inventory management can have a major impact on a company’s profitability. The findings in the report mean, that these companies have more goods in stock than they need. A product less in the warehouse does not only mean less tied-up capital, but also less warehouse space, reduced distribution, and administration costs and obsolescence (when a product becomes outdated).

Inventory optimization is not just about having fewer goods in stock. By always having the right mix of goods, missed sales are greatly reduced, while taking up less storage space and reducing the risk of an item being outdated. It provides an efficient recoil for the companies. They reduce costs while increasing revenue and freeing up capital.

Companies should reduce the inventory in specific categories of products, removing some SKUs, and minimizing the loss of revenues. They need to optimize the assortment without losing customers, taking into account, that customers may switch (together with all their purchases) to competitors if one of their favorite items is removed and it is not replaceable by any other.

The Traditional Inventory Approach
The Traditional Inventory Approach often entails removing SKUs that perform worst from the inventory, or in other words, remove products from categories that sell the least. Using this approach, it is possible that some clients are specifically interested in these SKUs, so that if they are discarded, customers are lost completely with all the revenues they bring.

A new algorithmic Approach
In contrast to the traditional approach, you can focus on removing SKUs which are indifferent to the consumer. With AI technology you have the possibility to predict if, from the consumer’s point of view, the removed SKU is replaceable by another item and we find the right match in term of profitability. In order to achieve this, our models, using only transactional data, answers the following inventory questions:

  • Frequent itemset mining – Which items are often sold together from a historical perspective?
  • Product alternativeness scoring – Which items provide good alternatives for items in the scope of removal?
  • Volume replacement scoring – How many customers actually buying item A will switch to item B if item A is removed from the inventory?
  • Revenue replacement scoring – Which portion of revenues is expected to be covered by the replacement product if the replaced product is removed?
  • Marginal replacement scoring – Which portion of margins are expected to be provided by the replacement product if the replaced product is removed?

Optimization Results
Our algorithmic approach has been tested side-by-side with the traditional method of removing least sold products and the algorithmic approach achieved 88% less estimated sales loss in the set of identified items for removal.

Are you looking for more information about AI and how you can incorporate it into your own Supply Chain – then you can download some of our great content via the below link.

Contact us to book a meeting

By clicking “Submit”, I agree to Optilons privacy policy.