Recommendations
Overview
Recommendations are AI-generated opportunities based on your sales data. Our advanced AI and machine learning models analyze customer purchase history to identify products they are likely to buy next. Each recommendation is tied to a specific customer and product, and users can act on them and track those actions through Interactions.
If your instance is integrated with SugarAI, recommendations are synced from sales-i to the Recommendations module. Refer to the sales-i SugarCRM Integration guide for more information on working with recommendations in SugarCRM.
This guide covers:
Working with Recommendations
Understanding Recommendation Fields
Each recommendation includes the following fields, providing key information about the potential opportunity:
| Field | Description |
| Customer | The name of the customer. This can be clicked to navigate to the customer record view. |
| Recommendation | The ID and name of the product being recommended to sell to the related customer. |
| Description | A description providing additional details on the recommendation. |
| Estimated Value | The estimated value of the recommendation which is the average unit price of the product multiplied by the suggested quantity. |
| Suggested Quantity | How many of the recommended product you are recommended to sell. This is based on our models analyzing your customers' buying patterns. |
| Expiry Date | The date the recommendation will expire. |
Actioning a Recommendation
Wherever a recommendation appears in sales-i, you can click the three-dot menu to either create a linked interaction or dismiss it. Refer to the Interactions guide for more information on working with interactions.
Viewing Recommendations
Once a recommendation is created, it is displayed in key areas across sales-i, making it easy to view and manage your recommendations.
Home Dashboard
The Recommendations section of your home dashboard displays all of your recommendations.
From this view you can:
- Search for recommendations by the customer and recommendation name using the search bar.
- Sort the Customer and Estimated Value columns by descending or ascending order.
- Click the three-dots menu to create an interaction linked to the recommendation or dismiss the recommendation if it is not valid.
Customer Record
If a customer has associated recommendations, they appear in the Recommendations subsection on the Opportunities and Details tabs of the customers' record. The recommendation subsection is separate from manually created CRM opportunities.
From these views you can:
- Sort the Estimated Value column by descending or ascending order.
- Click the three-dots menu to create an interaction linked to the recommendation or dismiss the recommendation if it is not valid.
Customer Snapshot Summary Report
If a customer has associated recommendations, they are displayed in the interaction history section of the customer snapshot summary report.
From this view you can:
- Sort the Estimated Value column by descending or ascending order.
- Click the three-dots menu to create an interaction linked to the recommendation or dismiss the recommendation if it is not valid.
Prerequisites
To generate recommendations, your instance must have sufficient sales data for the system to identify product associations. This requires at least 12 months of sales data, with an average of at least two different products purchased per customer. The number of recommendations generated will still depend on your specific sales data.
How Recommendations are Generated
After your instance meets the required prerequisites the recommendation process runs every time we ingest your ERP data which is typically once a day. Here is an overview of how recommendations are generated by our models:
- The last 365 days of sales data are analyzed and aggregated monthly to identify product association patterns where customers frequently purchase products together.
- The last 30 days of customer sales are then reviewed. If a customer has purchased one product in an identified association but not the related product, a recommendation is created.
- Invalid products are excluded from recommendations. This includes products excluded in your Associations settings, as well as common invalid items containing terms such as delivery, delivery charge, charge delivery, promotional, carriage charge, carriage, charge, freight charge, freight carriage, freight, rebate.
- Once a recommendation is created:
- If the related product association is updated, such as changes to suggested quantity or estimated value, the recommendation is updated accordingly.
- If the associated product is sold to the related customer before the expiry date, the recommendation is marked as “Won.” “Won” recommendations appear only in the “Won” tab on the Opportunities card of the customer record.
- If the recommendation reaches its expiry date before the associated product is sold, it is deleted. The default expiry window is 30 days.