Zappi’s Instant Digital Ad Predictor
Free AI powered ad predictions. Test now.
Think ad testing. Think of big brands like Coca-Cola. Think of expensive TV ads. If you’re a digital marketer, you might think it’s not for you.
That is about to change.
For the first time, test digital ads for free, in seconds. Real AI, real insights, powered by tens of thousands of consumer data points, and hundreds of millions of dollars of ad spend. Our new digital ad predictor provides a measure of your ad’s overall appeal, brand score, and ability to drive behaviour change, along with advice on how to improve it.
How to use the Instant (Free) Digital Ad Predictor
Three steps, and probably less than three minutes!
How it works
The Scores: Zappi uses a gradient-boosting machine learning algorithm to rapidly deliver a free prediction, based on a huge volume of anonymised and aggregated survey and norms data. What this means in layman’s terms is that a load of tags — both manually added and assigned algorithmically — are collected, cleaned, and fed into a decision tree model that then “boost” important components, while suppressing less important ones. This is the XGboost regression model. We’re using a machine learning model that predicts key metrics based on the attributes of the tested ad, e.g. branding, celebrity/human presence, length, etc. The model is trained on ads tested on Zappi Video/Digital and the prediction falls on average within 5% of the observed survey scores. We’re currently working on our V2, which will be far more accurate and specific.
Overall Appeal predicts whether the sentiment to the ad will be positive or negative.
Brand Score is A combination of how people feel about your brand, and how well your brand links into your ad.
Purchase Intent: how likely the ad is to drive behavior change, or make people purchase.
Enzo’s recommendations:Based upon Zappi’s meta analytics, industry and academic reports, white-papers, and experts, Zappi builds recommendation text based on what you have (and haven’t!) included.This insight is designed to be actionable, and help you rapidly improve your ad.
How to use your results
- Instantly get a basic scorecard with a few key measures. Judge how your ad might perform if you were to put it forward into full testing
- Get a few recommendations on how to improve performance. Making these changes, however simple, should improve your ad.
- If you want to learn more about your ad, carry on to Zappi’s full ad-testing platform.
Can I trust this model?
Yes, you can. It tells you based on history how strong your ad is. That is useful. And we constantly feed and re-train the model to make it better. But, it’s always going to miss some nuance — that’s what the full Zappi products are for.
What next?
To work out how to improve your specific ad, it’s always better to run a full project, with real consumers, on the Zappi platform. Understand how your ad performs now, with its intended audience. Do people like the ad? Are they likely to purchase your product after seeing the ad? Do they think your ad fits with your brand? Does it cause offence? Do your key messages land? Plus, you build a bank of your specific learnings that you can apply to your future creative strategy.
The free prediction depends on data that’s already out there — if your ad is groundbreaking or culturally relevant — or even just combines other features in previously unexplored ways, the free prediction could miss things.
V2
We’re strong advocates for agile development, and this is no different. We’re hard at work…
- Improving the model. We’ve got an upgraded taxonomy that we’re currently using to tag our test data. Additionally, we’re improving the way we consider your category/vertical, for ever more sophisticated benchmarking.
- Improving the recommendation engine. Actionability is key! We’re making sure Enzo’s recommendations are actionable, not just smart.
- Auto-tagging. We’re using Google Video Intelligence API to massively accelerate tagging and broaden the taxonomy. Watch this space.
