How does technology help media buyers get more out of their programmatic campaigns? Tim Conley at Iponweb, looks at ways an AI-based system really can make better decisions than a living, breathing human being.
There has been a lot of discussion about machine learning and artificial intelligence in recent years, but what do these terms really mean? For programmatic media buyers, it could be their secret weapon.
With the advent of Real-Time Bidding (RTB), brands and agencies were able to go far beyond what was possible with traditional media buying.
RTB enabled an explosive expansion of digital scale. Why? Because the sheer volume of data processed through programmatic pipes dwarfed that of the traditional digital channels. There was so much supply available, and it was being sent with so much additional metadata, that no human on earth would have been able to parse it – let alone store it.
Faced with a never-ending firehouse of inventory, media buyers needed a way to make split-second, data-driven decisions reliably. Originally, it was a matter of simply discarding data and inventory with broad strokes to optimise campaigns. This meant that high quality inventory could inadvertently be culled because – from a human’s perspective – it was indistinguishable from the poorly performing inventory.
Over time, as machine learning models became more sophisticated, it became possible to be far more selective about the opportunities coming through the bidstream… and the floodgates opened.
This algorithmic approach to media buying meant that users could decide on the supply that best suited their goals, and what to bid for those opportunities, based on hugely expanded criteria, including first-party and campaign data, and bidstream signals.
Algorithms can leverage plenty more sources of information, but the central point is that there’s so much data being sent through programmatic pipes so quickly that no human could ever keep up.
It’s here that machine learning really comes into its own.
Human-powered programmatic optimisation
While machines might have the edge, particularly in terms of speed, humans still bring a lot of value to media buying:
• We are able to process and take action on client briefs, meaning the actual planning of a campaign can only be done by a human. In addition, the ability to plan media buys based on intuition, human context, and experience will always be critical to a well-executed campaign.
• We can leverage more fine-grain tools based on external factors, such as inclusion / exclusion lists and manual bid multipliers to enhance the strategies and priorities defined in the media plan.
• Beyond the nuts and bolts, we can bring our creativity into the mix with creative design, copy, and the big ideas that power large-scale campaigns – something machines are quite some way from achieving.
So, what about the drawbacks of being human when buying media?
To better illustrate them, let’s use a practical example based on a media buyer’s everyday life: managing line items.
Without the assistance of a computer or machine learning algorithm, every line item of a campaign would need to be manually assessed on an ongoing basis. The media buyer might have a database of historical campaign performance, from which they can pull key data points to use for optimisation: audiences, time of day, creative sizes, supply source, and so on. Each line item would need to be cross-referenced against historical data and the insights leveraged to make planning decisions.
All of this takes time – even the best data scientist in the world with the most comprehensive dataset on the planet wouldn’t be able to compete with a machine, because humans have a hard limit of how much we can process – and how fast we can act on that data.
The scope of our decision-making is also limited by the range of the dataset we can manually parse. For example, there may be a strong correlation between two line items and the audiences they were assigned: audience A delivered better results than audience B. Seems straightforward enough.
But what if there are other correlations that aren’t explored? The bandwidth of our attention simply prevents us from being able to compete with machine learning models head-on.
How machine learning can help media buyers
Now that we’re familiar with what people can bring to the table, what about machines?
Machine learning – computer systems that are able to learn and adapt without following explicit instructions, by using algorithms and statistical models to analyse and draw inferences from data sets – opens the door to a host of benefits, such as:
• Algorithms can make thousands of decisions per second with – crucially – no second-guessing. Subjectivity is left at the door, because all media buying decisions are made by the data – for good or for bad.
• Machine learning can instantly call on huge volumes of historical data from previous campaigns. What worked? What didn’t? This data can be used to train a model before a media buy is made.
• Because algorithms get better the more data they have to pull from, machine-based decisioning offers continuous improvement and optimisation leveraging every dimension of data available. Where the human knows the audience A works better than audience B, the machine can see which supply sources, creatives, geos, and more correlate best with performance and selects optimal bid prices for each impression in real time. No more throwing the baby out with the bathwater
• This creates the ability to launch largely automated campaigns with minimal human intervention that help advertisers achieve scale – and fast. Buyers can simply replicate previously successful campaigns, tweak a few parameters, and go live in moments.
The hybrid future of programmatic advertising
Now that we have a clearer vision of the part machine learning plays in this ecosystem, where does the future of programmatic media buying really lie?
Smart programmatic media buyers need to take the best of both and utilise a hybrid model.
The benefits of human input – creativity, intuition, logic, emotion, goal-setting – remain critical to effective media buying. Machine learning is a powerful tool, but it should be used in combination with everything people can bring to the table.
So, in a perfectly balanced programmatic process, humans will do the planning and set the direction of the campaign, and machines will execute and optimise it with real-time decisioning to supercharge campaign results.
By Tim Conley
Client Services Director, Europe