To curate effective product pages, it is essential to understand the impact of exposure strategies. These strategies determine how products are ranked in product lists. By conducting A/B testing, you can optimize Elevate's exposure algorithms to align with specific business goals.
There are three different exposure strategies available and can be set per market in the Business application area.
- Conversion Focus: Prioritizing actions that lead to higher conversion rates, by exposing products that sell more.
- Revenue Focus: Maximizing overall revenue, by exposing higher priced products.
- Profit Focus: Enhancing profitability by tailoring exposure strategies to expose high margin products.
Product ranking
Each product in a given context has a momentary popularity value, a strategy score, based on the selected exposure strategy. Each individual product score is continuously re-evaluated based on sales data, and will affect the listing position of the product in every context.
A/B testing
Before selecting an exposure strategy it is recommended to perform a built in A/B test between the strategies. An A/B test will establish the effect of switching exposure strategy on a site.
Metrics for conversions, revenue, and profit can be monitored throughout the test period. Predictions of the impact of a strategy switch are made and visualised. The longer a test is ongoing and the more sessions that are affected, the more exact the predictions will be. The results and predictions will provide a merchandiser with information on how the different strategies affect goal metrics and inform of potential trade-offs.
This form of testing of competing strategies is built into Elevate and allows for merchandisers to make an informed decision based on actual performance.
| Prediction | Description |
| Range of impact | The range of impact is a value that represents the predicted change per metric in percent for the queries affected by exposure strategies when switching from strategy A to B. The expected impact is given as a 95% confidence interval with an upper and lower bound. |
| Total impact | The total impact is a value that represents the predicted change per metric in percent for all queries when switching from strategy A to B. |
Use cases
The key use cases for exposure strategies includes payday optimization and discount period optimization.
Primary lists and recommendation lists
Primary lists and recommendation lists can utilize exposure strategies. Primary lists fully utilize exposure strategies when using the "RELEVANCE" sort order. Recommendation lists fully utilize exposure strategies when using the "TOP_PRODUCTS" algorithm, and partially utilize exposure strategies, i.e. on product backfill, for the other recommendation algorithms.
Article last updated