Create a Ranking Algorithm in Algorithm Studio

Create a ranking algorithm to rank products based on their performance and attributes from your product feed. You control which factors to consider, how much weight each factor carries, and the time frame for evaluating the user behavior that affects your algorithm.

Step 1: Define the factors to consider and their relative impact

1. Go to Algorithm Studio › Create Algorithm, and select Ranking. 
   
2. Name your algorithm. The algorithm is used in Experience Email or recommendation strategies, so keep the name short and descriptive. For example, “Trending Products,” “Trending by Views,” or “Bestselling Offline.”

3. Select up to four ranking factors.
   

   Note: Only product feed columns reported with type number are available in the Product Attributes section. A product is scored and ranked as part of an algorithm with a product attribute factor only if it has a valid numeric value in all its number-type fields.

4. Define each factor's relative weight and ranking direction. Select high to low to prefer products with high factor values, or low to high to prefer products with low factor values. For example, for Return Rate, select low to high so that products with lower return rates are ranked higher.

The factors you select and their relative weights determine how your products are ranked. For example, selecting only Purchases creates a Best Seller algorithm. Selecting Purchases, Review Score, Return Rate, and Sale Price creates a Top Picks algorithm that considers multiple product performance and attribute factors.

Step 2: Define the product performance lookback window

Define how far back the algorithm considers product interactions when calculating the ranking. For example, to create a “3 Days Trending” algorithm, use a three-day data window.

Step 3: Select an audience to factor by

Learn what your audiences like and apply it to your recommendations. Select an audience whose behavior you want the algorithm to consider. The audience must contain at least 1,000 users.

Step 4: Preview the results

Before saving your algorithm, preview the results to see how the algorithm ranks your products. Depending on the size of your product feed and the volume of your data, calculating the preview might take up to a couple of minutes.

Step 5: Save the algorithm

When you save the algorithm, its status is Pending. Depending on the size of your product catalog, the initial processing can take up to several hours. The algorithm is recalculated whenever your product feed syncs. For API product feeds, the algorithm is recalculated every 12 hours.

Step 6: Use the algorithm in your strategies

After the algorithm is processed for the first time, it appears in the algorithm dropdown on the Create Strategy screen. The dropdown includes the algorithms created in Algorithm Studio and the built-in Dynamic Yield algorithms. Select the algorithm, and apply merchandising rules and filters as needed for your use case.

Limitations

• You can create up to ten algorithms, but only five can have an audience-based product performance setup.
• The Product Performance by Audience section includes only audiences with at least 1,000 users.
• Algorithm Studio algorithms are section-specific. Strategies that use custom algorithms created in Algorithm Studio can't be copied between sections.