As parents everywhere will attest, the most frequent and difficult question to answer is without doubt ‘why?’. From an early age people want to know the cause or driving force of everything and it’s often the hardest question to answer.

It’s certainly a challenge when trying to identify how artificial intelligence (AI) algorithms drive uplift. We know the uplift is there, it’s clear to see from quarterly results that entertainment campaigns on average see 151% uplift, retail 135% and technology 96%. But where it becomes more difficult is in establishing the individual factors which have produced this uplift.

Each time an impression is about to be served information is pulled from trillions of data points which are stored in a Data Management Platform. This data can be broken out into factors such as gender, age, household income, operating system, device manufacturer, device models, battery life, how a device is charged, weather, home location, office location, location habits (how often does someone travel and where to for example), which apps are downloaded, which sites are visited, which time of day promotes the most interactions etc. The list goes on.

A huge amount of data is processed to determine how likely a user is to interact with any given ad at any given time. AI makes it possible to take all the data available to technology providers and transform it into actionable insights which allow campaigns to be served to the users who are most likely to engage with a piece of content at that moment in time.

Factors such as the time of day, device and user profile will have an impact on how likely a campaign is to generate an engagement. Broadly speaking these factors can be ranked as to importance, but this will certainly vary from campaign to campaign and may even change throughout the course of a day. For example, a campaign for a summer drink like Pimms will probably be largely dependent on the weather while user behaviour might be a more significant factor for a Game of Thrones trailer. Different elements will have more or less influence depending on the advert.

However, that does not mean that secondary factors are not important. Each factor will have an impact on each campaign to some extent, and removing any one of those factors could make a significant difference to a campaign’s performance. For example, weather might be the most significant factor in determining engagement in an advert for Pimms.

But consider that location data could be used to target regular Tesco shoppers where the drink is on offer, user behaviour could identify people who have engaged with similar content in different environments or engaged with advertising when using a particular app. Remove any of these pieces of information and it becomes harder to target the users who are the most likely to engage with the advert.

If we break out key driving factors for each campaign and isolate them then there is a risk a significant factor, which could dramatically alter campaign results, is not identified as important. AI is able to hold each of these factors in perfect balance to attain significant campaign optimization. By analysing huge volumes of data across a wide range of factors AI is able to improve campaign results.

When looking at ROI, AI allows campaigns to be optimized across a range of KPIs - CTR, VCR or post click events (app installs etc). Having tested this, across all the campaigns run using AI, CTR was improved by an average of 130.8%, VCR by 70.8% and Post Click Events by 103.9% compared to each campaign’s control which did not use AI. This means that brands received more interactions with their content, not by using different publishers, formats or creative, but by using AI to identify and exploit patterns in behaviour which were the most likely to generate a desired outcome.

By improving the results of campaigns across all metrics and delivering adverts to users who are the most likely to engage it’s possible to improve brand metrics and deliver real return on investment for brands using AI.


By Stephen Upstone, CEO and founder, LoopMe

PrivSec Conferences will bring together leading speakers and experts from privacy and security to deliver compelling content via solo presentations, panel discussions, debates, roundtables and workshops.
For more information on upcoming events, visit the website.

comments powered by Disqus