Exposure strategies¶
Exposure strategies is a concept that enables merchandisers to have Voyado Elevate optimise its algorithms for product exposure towards different business goals.
Disclaimer
App designs and features are subject to change without notice. Screenshots, including simulated data visible, are for illustrative purposes only.
There are three different exposure strategies available and are set per market in the Business app.
- Expose higher priced products (Revenue focus)
- Expose high margin products (Profit focus)
- Expose products that sell more (Conversion focus)
Product ranking¶
Each product returned in a panel supporting exposure strategies has a momentary popularity value, a strategy score, based on the selected exposure strategy. The optimal period of time for the strategy score is automatically and individually chosen per product.
The strategy score determines in what order products will be returned when querying a panel to list products using the Sort by relevance sort order as primary or secondary sort level.
Exposure strategies also work when using the Search hits panel by itself or in a zone. The panel must use the Sort by relevance sort order as the primary sort level in the sort_by
argument.
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 panels 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 panels when switching from strategy A to B. |
Use cases¶
The key use cases for exposure strategies include payday optimization and discount period optimization.
Panels supporting exposure strategies¶
Depending on what panel is used, exposure strategies are utilized either fully or partially. Panels that partially utilize exposure strategies, such as the Autocomplete panel, use exposure strategies on product backfill. Multi-level sorting will affect exposure strategies.
Exposure strategies are fully utilized in:
- Product list panel, when using relevance or sales as sort order
- Product list with count zone, when using relevance or sales as sort order
- Search hits panel, when using relevance or sales as sort order
- Search hits with count zone, when using relevance or sales as sort order
- Search zone, when using relevance or sales as sort order
Exposure strategies are partially utilized in:
- Product list panel, when using personal as sort order
- Product list with count zone, when using personal as sort order
- Autocomplete panel
- Did-you-mean panel
- Product suggestions panel
- Ad information panel, for products in a live ad
- Ads by customer panel, for products in a live ad
- Ads by product panel, for products in a live ad
- Ads by search panel, for products in a live ad
- Top ads panel, for products in a live ad