Predict your campaign
What is it
The AdForecaster is the next-generation forecasting engine for online advertising campaigns. It overcomes various important limitations of existing forecast engines in ad servers, allowing you to accurately predict future ad impressions traffic levels and campaign inventory availability using an unlimited number of targeting variables, including geo, keywords, key-values, cookies and multiple frequency capping groups at banner, booking, line item or campaign level.
It is operated as a Software-as-a-service, minimising integration and deployment times as well as operational maintenance costs.
Custom-built Ad Servers and Exchanges, Sell-side platforms (SSPs) and Demand-side platforms (DSPs) are the most common type of platforms that can take advantage of the AdForecaster.
The importance of ad forecasting
- The highest yielding campaigns typically require a volume guarantee.
- Agencies and Advertisers rely on commitment to deliver their budgets and goals.
- Inventory owners depend on their forecast to commit to delivering campaign volumes.
- An unreliable forecast means inventory goes unsold unnecessarily.
- Overselling and under-delivering ensures budgets will go somewhere else.
Premium publishers and networks are the first to suffer from unreliable forecasting as soon as they start overlaying data with their inventory, which they are compelled to do in order to increase the value of their inventory.
For Exchanges, SSPs and DSPs
The “automated channels” are already data-driven but have been focused on RTB and performance. In order to grow their service offering with guaranteed campaign delivery they require accurate and scalable forecasting engines.
For Ad Servers
Ad Server providers require a forecasting engine capable of using all the data their clients are throwing at it, or risk being replaced by another provider who does.
Why a specialised tool is a good idea
The growth of data available for campaign targeting is making traditional forecasting methods obsolete, as spreadsheets or even standard ad server forecasting tools are no longer able to produce reliable forecasts.
The main reason is their approach: looking at aggregated counts by site, channel, packages and a limited set of variables, instead of individual users and ad requests.
The more data overlaps, e.g. Channel News and Male Demographics, the more inaccurate these approaches become, compounded by the increased used of 3rd-party data targeting, frequency capping and booking complexity.
Where does it fit
The AdForecaster sits at the centre of your Online Advertising Platform, answering questions from you campaign management GUI/Services when they require the knowledge of how many unique users and ad impressions are available for a campaign.
How it works
State of the art engine
Future inventory is predicted based how sections and segments grow or shrink and how they vary with the hour, week day, month and season. New inventory sources available in 24 hours, automatically detected and forecasted based on as little as 1 day of traffic.
Simulating millions of browsers hitting your ad decision logic is the most accurate way for predicting availability, as it ensures all variables and campaigns are taken into account.
The AdForecaster does this with unprecedented efficiency, making simulation-based forecasts affordable to everyone.
First results within seconds, further results with increased accuracy
Adaptive decision engine
Customised to mirror how your AdServer works
Handles unlimited targeting variables
Capable of taking into account any combination of targeting parameters you use in your AdServer such as Geo, Keywords, Key-Values, Cookies, Segments, etc.
Multiple frequency capping groups
Capable of forecasting the most complex frequency capping scenarios with multiple restrictions set at the Campaign, Booking, Banner or any other level set in your AdServer
Seamless integration with your and third-party platforms via APIs
Cloud-based architecture means only exactly the required processing power is brought to bear for the forecasting task, minimising costs while maintaining performance.