You are here:
B2C Commerce Einstein Recommender Strategies
After determining which recommenders you plan to use, specify recommendation strategies. This topic applies to B2C Commerce.
Strategies represent different approaches―different algorithms―for generating lists of recommendations (product IDs). When generating a list of recommended product IDs, B2C Commerce Einstein employs one or more of the strategies listed in the table.
The best practice is to select at least a primary strategy and a secondary (fallback) strategy. But select up to three strategies. Strategies apply in the order that you select them. In the rare case the first strategy doesn't return recommendations or has insufficient data to produce high-quality results, the second strategy backfills to send recommendations to the page.
The order of strategies matters. The first strategy listed takes priority over the second strategy, which the system uses only if the first strategy fails to generate enough recommendations. The second strategy takes priority over the third strategy, and so on.
This table lists the supported strategies, a brief description, and the recommender type for which the strategy is available.
Salesforce recommends that you specify at least two strategies, so that if the first strategy fails to return enough recommendations, the system can use the second strategy. Specifying at least two strategies is best practice. However, the Recently viewed recommender type is an exception, as it applies only one strategy.
We recommend using the first strategy based on an individual’s real-time behavior. This table shows strategies that use individual customer experience and history blended with the entire customer base of your site.
| Strategy | Anchor Expected | Result |
|---|---|---|
| Product affinity algorithm | product-id | Einstein uses model-generated affinity recommendations based on the purchase history of the entire customer base. |
| Real-time personalized | None | Einstein returns the highest ranked products for a specific user based on the user’s recent browsing history. The most recent four products that the user is most likely to be interested in viewing next appear. |
When choosing a second strategy, choose one that applies to your site's entire customer base. Then use other strategies based on an individual's history. Using multiple strategies provides a more personalized experience for both new and existing customers.
This table shows strategies that use the entire customer base of your site.
