Documentation Index
Fetch the complete documentation index at: https://docs.aftersell.com/llms.txt
Use this file to discover all available pages before exploring further.
Post-Purchase Multivariate Testing
Multivariate testing lets you test multiple offer variables at once - like discounts, timers, and product selections - to find the best-performing combination. You define the variables and select the options you want to test, and Aftersell combines them into all possible layout combinations for testing. It’s one of the most powerful ways to optimize your post-purchase upsell strategy.In multivariate testing, you define individual variables and their options, and Aftersell combines them into all possible layout combinations for testing. If you want to configure complete layouts individually and test them against each other (up to 5 layouts), use Post-Purchase A/B Testing instead.
Multivariate testing is only available for post-purchase (one-click) upsells. Multivariate testing for Thank You page offers is not currently available. For checkout widget testing, see Checkout A/B Testing.
1. Define your goal
Before setting up your multivariate test, take a moment to define what success looks like for your store. Setting a clear objective helps you choose the right variables to test and measure what truly matters. Some popular goals include:- Increasing conversion rates on upsell offers
- Boosting average order value (AOV)
- Identifying the most effective product or incentive
2. Choose the variables to test
Select 1-5 high-impact variables that could affect buyer behavior. For example:- Product selection: Specific product vs. AI recommendations
- Discount type: Percentage vs. fixed dollar vs. no discount
- Urgency timer: 5 min vs. 15 min
- Shipping: Free vs. flat-rate
3. Create your variations
Set up options for each variable. For example:- Discounts: 10%, 20%, 30%
- Timers: 5, 10, or 15 minutes
- Products: Single product vs. multi-product offer
4. Set up your multivariate test
- Open the Aftersell Dashboard
- Go to Post-Purchase Funnels
- Create a new funnel or open an existing one
- Click Create test and select Multivariate Test
- Select your desired variations
- Click Start test
Be sure to press Enter after typing in each variable to save it properly.
How traffic is split
Traffic is automatically distributed evenly across all layouts generated by the test. There is no way to manually adjust the traffic percentage for each layout. For example, if your variable combinations produce 4 layouts, each layout will receive approximately 25% of traffic. There is no option to set custom percentages (for example, you cannot set Layout A to 80% and Layout B to 20%).5. Review the results
Once your test has been running for a sufficient amount of time, ideally 2-4 weeks, you’ll have enough data to make informed decisions. Shorter test durations may not yield statistically reliable insights, especially if traffic is low. To view your results, go to the Tests tab in your Aftersell Analytics dashboard. For a complete breakdown of all Tests tab metrics, including group-level analytics, Performance by Variable, the All Groups table, and how to select a test, see Post-Purchase Analytics.6. Apply the winning variation
Once a winner emerges:- Apply that variation across your funnel
- Monitor performance to ensure it continues delivering strong results
- Consider testing again with a new set of variables
Limitations
Multivariate testing is within a single funnel only
Multivariate testing runs within the same funnel. You cannot run a multivariate test across multiple funnels.Multivariate testing is for post-purchase (one-click) upsells only
Multivariate testing is not currently available for Thank You page offers. It is only supported for post-purchase one-click upsell funnels.Custom traffic percentages are not supported
Traffic is always split evenly across all layouts generated by the test. There is no option to assign custom percentages to individual layouts.Multivariate test vs. A/B test
Not sure which testing method to use?| Multivariate Test | A/B Test | |
|---|---|---|
| How it works | You define individual variables and their options, and Aftersell combines them into all possible layout combinations for testing | You manually configure each layout as a complete offer and test them against each other |
| Layouts | Based on your selected variable combinations (Layout A, B, C, etc.) | Up to 5 layouts (Layout A through E), each manually configured |
| Best for | Finding the best combination of individual variables (discount, timer, product, etc.) | Comparing complete offer designs against each other |
| Traffic split | Evenly across all combinations | Evenly across all layouts |
| Statistical significance | Requires more traffic due to more combinations | Faster to reach with fewer layouts |
| Results | More complex - identifies best combination of variables | Easier to interpret - one layout wins |
- You want to test multiple variables simultaneously and find the best combination
- You have high traffic levels
- You want to define variables and have Aftersell combine them into layout combinations for testing
- You want to compare complete offer configurations
- You have moderate traffic levels
- You want clear, straightforward results
Best practices
- Start simple: Don’t overload with too many variables
- Be patient: Let tests run long enough to collect data (minimum 2-4 weeks)
- Keep testing: Use winners to inspire your next round of tests