When we buy something on JINGdong or Taobao, the app will automatically recommend us some other products that we may buy. These recommendations are calculated by the machine learning framework based on our previous purchasing habits through certain algorithms.

SAP’s CRM Cloud solution, Cloud for Customer (C4C), also supports product recommendations using machine learning for up-selling and cross-selling opportunities based on sales order history data.

Let’s take a look at the implementation of ai in the product recommendation scenario. Once again, go to Administrator->Prediction Services and click Model Setup to set the Model for machine learning.

We can see the Product Recommendation in the Machone Learning Scenarios list. Click the button “Add Model” to create a new machine learning Model, click “Train” for training, ensure that the training is successfully completed, and the status changes to “Active”, indicating that the Model is available.

Create a new Product List containing the products you want to sell: the following example has two products with ids 1042416 and 10001380.

In the traditional Product recommendation scenario, if I want to recommend some other Products after maintaining the ids of the above two Products in the line item of the sales order, I need to manually maintain these recommended Products into the “Proposed Products” TAB of the Product List. As shown in the red area below.

With artificial intelligence and machine learning, these manual configuration steps and work can be eliminated. I have added a “203-product Recommendation” scene to this Product List, as shown in the blue area below, hoping that the products contained in this Product List will be added to the sales order. SAP C4C system will automatically recommend related products to me through artificial intelligence.

Now let’s do a test, create a new sales quotation, and put a Product previously maintained in the Product List, such as 1042416, in the line item of the sales quotation. Then the C4C system automatically recommended two other products to me, whose IDS are P140101 and P140100.

For more of Jerry’s original technical articles, please follow the public account “Wang Zixi” or scan the following QR code: