Related Items in Sales Orders: Automated Suggestions for Cross-Sell Items

Automated cross-sell generation in MYOB Acumatica helps you identify and suggest cross-sell items for stock and non-stock items without relying on manual setup. By analyzing your sales history, the system uses machine learning to create relevant cross-sell suggestions that save time and uncover opportunities you might otherwise miss. Once you configure the process, it can run on a schedule or on demand, reducing repetitive work for your team.

Applicable Scenarios

Automated cross-sell suggestion generation is useful if your company manages a large product catalog and manual setup requires significant time and effort.

Enable the Needed Feature

To enable the Related Item Assistant feature, which is required for automated generation of suggestions in MYOB Acumatica, do the following:

  1. Open the Enable/Disable Features (CS100000) form.
  2. On the form toolbar, click Modify, and select the Related Item Assistant check box under the Inventory and Order Management group of features.
  3. On the form toolbar, click Enable.

Specify Basic Generation Settings

You specify the initial settings of automated cross-selling suggestions on the Machine Learning tab of the Sales Orders Preferences (SO101000) form.

In the Cross-Sell Assistant Settings section, do the following:

  • In the Data Period for Analysis box, specify the time range for the database records of AR transactions used in analysis and generation. Use a shorter period if your set of items changes frequently. Select one of the following options:
    • 3 Months
    • 6 Months
    • 1 Year (default)
    • 1.5 Years
    • 2 Years
  • In the Min. Relevance Score (%) box, specify the minimum score of relevance for items that the system suggests as cross-sells. You can specify any value from 50 to 100.

    The ML model calculates the relevance score based on several factors, such as the frequency of joint sales of items. Setting the relevance score too high may lead to a small number of suggestions. Setting the relevance score too low may bring suggestions that are weak.

  • In the Max. Number of Suggestions box, specify the maximum number of ML-generated suggestions the system can add to the Related Items tab of the Stock Items (IN202500) and Non-Stock Items (IN202000) forms after each generation. For more details, see Limit the Number of Generated ML Suggestions.
  • You can also select the Add Relations as Active check box to make the system do the following:
    • Remove all suggestions of related items created during the previous suggestion generation. The system does not remove related items that were manually added on the Related Items tabs of the Stock Items and Non-Stock Items forms.
    • Make new suggestions immediately active on the Related Items tabs of the Stock Items and Non-Stock Items forms.

You can also specify the following settings on the Machine Learning tab:

  • Select a notification the system will send as soon as it generates suggestions in the Generated Suggestion Notification box.
  • Add a class to the Excluded Item Classes table if you need to exclude the items in any item class from the generation.
  • Add an order type to the Excluded Order Types table if you need to exclude the AR transactions generated by this order type from the set of records used to generate cross-sell suggestions.

Limit the Number of Generated ML Suggestions

You can limit the maximum number of ML-generated suggestions the system can add to the Related Items tab of the Stock Items (IN202500) and Non-Stock Items (IN202000) forms after each generation. You specify this number in the Max. Number of Suggestions box on the Sales Orders Preferences (SO101000) form. The Add Relations as Active check box on the same form affects this number as follows.

  • If the check box is selected, the number limits both approved and unapproved suggestions.
    Tip: A suggestion is unapproved if the Accepted ML Suggestion check box is cleared on the Related Items tab.
  • If the check box is cleared, the number limits only unapproved suggestions. The system does not take into account approved suggestions.

Suppose that a stock item has 3 approved and 2 unapproved suggestions on the Related Items tab of the Stock Items form. In the Max. Number of Suggestions box, you have specified 3. On the next generation, the ML model has returned 4 suggestions. The resulting number of suggestions added to the Related Items tab will depend on the state of the Add Relations as Active check box as follows

  • Selected: The system deletes all existing suggestions and adds 3 of 4 suggestions of the latest generation with the highest relevance score. The total number of suggestions on the Related Items tab becomes 3. If any of these suggestions previously had the Accepted ML Suggestion check box selected, they remain approved.
  • Cleared: The system adds only 1 unapproved suggestion with the highest relevance score. The number of unapproved suggestions becomes 3, the total number of suggestions is 6.

Refine Generation Settings

For greater precision in the generation of cross-selling suggestions, you can refine generation for any item class. These settings affect all items in the selected class. You do this on the Machine Learning tab of the Item Classes (IN201000) form.

In the Cross-Sell Assistant Settings section, you do the following:

  • Preferred Item Classes: Select whether the system will suggest items of the same class, other classes, or any class as the cross-sell item.
  • Price of Suggested Items: Select whether the system will suggest items with lower default prices only or items with any default price. The system uses the default price of items on the Price/Cost tab of the Stock Items (IN202500) and Non-Stock Items (IN202000) forms.

You can also adjust these settings at the item level on the Related Items tab of the Stock Items and Non-Stock Items forms.

Start the First Generation

To generate cross-sell suggestions, you click Process on the Generate Cross-Selling Suggestions (ML504000) form. The system analyzes stock and non-stock items, along with sales documents that include them. Based on selling patterns, the system creates cross-selling suggestions.

You can monitor the process stage in the Progress box. Also, the system displays informational messages with the number of steps in the process.

You can use the Frequency box to schedule weekly or monthly automatic generation or keep it manual by selecting the On Demand option.

Analyze Data Sent to the ML Model

To review the data that is sent to the ML model, you can also use two generic inquiries. These inquiries aren’t visible to non-administrative users in searches or workspaces; they can be opened only from the Generic Inquiry (SM208000) form:

  • IN-CrossSellWithML: Lists the AR transactions used in the generation of suggestions.

    You can use this generic inquiry to filter the data that’s sent to the model. On the Conditions tab of the Generic Inquiry form, modify the conditions to include or exclude certain transactions. For instance, you can this filtering to exclude a customer whose purchasing behavior shouldn’t influence suggestion results.

  • IN-RelatedItemFeedback: Records user feedback. Each time a user approves or deletes a suggestion, information about it appears in this generic inquiry.
Important: Avoid modifying these generic inquiries. Modifications could cause errors to appear when users run the generation of suggestions. If needed, restore the generic inquiries to their original state.

Manage Cross-Selling Suggestions

When the system completes the generation of cross-selling suggestions, you approve or delete them on the Manage Cross-Selling Suggestions (IN503500) form. Suggestions also appear on the Related Items tab of the Stock Items (IN202500) and Non-Stock Items (IN202000) forms.

Attention: Matrix items are treated the same as regular stock or non-stock items during cross-sell suggestion generation.

You can approve or delete any number of suggestions by selecting the appropriate option in the Action box on the form toolbar. To process only particular suggestions, you can select the unlabeled check box for each suggestion and click Process on the form toolbar. Alternatively, you can process all suggestions at once by clicking Process All. If you approve or delete a suggestion, the system will not show it on this form after the next generation. The ML model reduces the score of the deleted suggestions.

When you approve a cross-sell suggestion, the system selects the Accepted ML Suggestion and Active check boxes for the cross-sell item on the Stock Items or Non-Stock Items form. You can also approve or delete suggestions directly on these forms. If you have selected the Add Relations as Active check box on the Machine Learning tab of the Sales Orders Preferences (SO101000), you do not need to perform manual approval because the system selects the Active check box automatically. You approve the suggestions only to send positive feedback to the ML model.

View All Non-Deleted Suggestions

When you approve a suggestion on the Manage Cross-Selling Suggestions (IN503500) form, the system removes it from the list. If you need to review all suggestions—including approved ones—you can find them all on the Cross-Selling Suggestions (IN409500) form.