❓ Frequently Asked Questions
Account Creation FAQs
Is the data I input to GeoLift by Recast safe?
Recast is SOC-2 certified and compliant and is committed to keeping your data safe and secure. When you upload data to GeoLift by Recast, Recast will never share that data with anyone else. Recast may use data for developing anonymous, aggregate-level reports on industry trends, but the data will never be linked back to individual companies or users. You can see our SOC-2 compliance at trust.getrecast.com and read more in our Terms of Service.
What will GeoLift by Recast cost after the trial period?
We're still finalizing pricing, but like with our free trial, the goal will be to make the ongoing price extremely affordable so that brands of all sizes can access great experimentation tools.
Do I need a credit card to start my GeoLift by Recast trial?
No! Access to GeoLift by Recast is completely free and unlimited for six months. No credit card required.
We're an agency. Can we use GeoLift by Recast on multiple clients?
Absolutely. During your six month trial, GeoLift by Recast is completely free to use across clients.
Platform Usage FAQs
What are the limitations of Geolift by Recast?
Advertising buys must allow geographic targeting – if it’s hard to limit spend inside a geography and there’s spillage to surrounding geographies, the estimates won’t be as accurate.
GeoLift provides point in time estimates – unlike MMM, the performance measured from a GeoLift test applies to a particular point in time. Measuring different points in time would require running a new test. Recast’s Bayesian MMM works well with the GeoLift by Recast output as we estimate incrementality for each channel every day. This means we can apply the knowledge gained from the GeoLift model accurately to the specific time when the test was run without making assumptions about marketing performance over time.
Heterogeneous geos- If different states have different demographics who respond differently to ads, the results will be less accurate
Outliers - eg. a major localized event during the test period could skew the results.
How does GeoLift by Recast work statistically?
GeoLift by Recast uses a statistical method called augmented synthetic controls to help estimate the incremental effect of the experimental change. When running an experiment, you typically want your test and control groups to be as similar as possible (except for the treatment). Synthetic control models help with this by analyzing the pre-test period and assigning each control geography a weight such that when you sum up the conveions in the control group, it is as close to the test group as possible. Then, these weights are used when analyzing the experiment to determine if the change in conversions in the test group was caused by the spend changes or by random fluctuations.
How long should my test be?
The tool will allow you to test different experiment lengths, and will warn you if it can’t find feasible designs for a particular length. However, we generally would not recommend going under two weeks and think a month is a good starting point for most businesses.
Can I run concurrent (or multi-cell) tests?
GeoLift by Recast supports analyzing tests that were run concurrently, but is not currently set up to provide optimal designs in the case of concurrent tests.
When analyzing the tests, the important thing to do is when analyzing test #1, exclude all test locations from test #2, so that they’re not used in the control when building the model. Similarly, when analyzing test #2, exclude all test locations from test #1.
While you can still use our tool to design concurrent tests, they may not be optimal because there’s no way to precisely control it so that the other experiment’s test regions don’t appear in the controls of the second test, as each change to the exclusions will change the set of test locations recommended. If you are only testing in a small percentage of all locations, these problems will likely be minimal. These problems will be more pronounced if you’re testing in a large percentage of all your regions.
In the future, we plan to expand our multi-cell capabilities.
Can I test multiple channels or only one?
If you want to test multiple channels at once (for example, to get an estimate of “brand marketing” performance as a whole), you can certainly use GeoLift to design and analyze those tests. However, it may make it more difficult to use the test to configure a Recast MMM (or any other MMM for that matter) because we won’t be able to get precise ROI/CPA estimates for each channel but only for the collection of channels that you tested.
Sometimes when I try to login nothing ever loads. How can I work around this?
This is a known issue that we’re working on. As a workaround, opening the website in a new browser (or a Chrome Incognito window) will typically properly allow the page to load.
What if I don’t know the exact locations for some of my revenue/conversions?
If some of your revenue is not mappable to a specific location, we recommend excluding it from your dataset entirely. We do not recommend lumping all unknown revenue into a single location. Allowing an “unknown” location to serve as a test or control geography will make your GeoLift test less accurate.
How should I think about running incrementality tests during holidays?
We recommend you check out this blog post for tips and advice.