Jamillah is the UK Editor for The Next Web. She's based in London. You can hear her on BBC Radio 5Live's Outriders. Follow on Twitter @jemi Jamillah is the UK Editor for The Next Web. She's based in London. You can hear her on BBC Radio 5Live's Outriders. Follow on Twitter @jemimah_knight or drop a line to [email protected]
There’s nothing like a little science to make everyday processes a little more interesting and there’s no reason why digital advertising could not do with a little artificial intelligence expertise to see what will come from that mix.
Academics from the University of Brighton are doing just that by bringing mathematics and computer modelling techniques to develop new systems for the digital advertising services company, Crimtan.
The link between academia and business has been organised via a Knowledge Transfer Partnership (KTP), a system that was recently approved by the UK government’s Technology Strategy Board. In plain English that means that companies can access great minds in universities and colleges while academics can put their knowledge to practical use in business.
The academic’s expertise in artificial intelligence (AI) will applied to brands so that they can benefit from the research as part of a new portfolio from Crimtan for real-time, targeted advertising that also aims to protect user privacy. This should automate online advertising processes and decision-making by mirroring human expertise and experience.
Put plainly, the technologies developed here should mean much faster and more intelligent decisions such as which specific creative form a brand campaign should take and how or when it should be shown to a particular user. The application of AI in advertising with technologies to create targeted campaigns should help to make this type of promotion more useful and less creepy.
The project will be led by Professor Miltos Petridis and supervised by Dr Roger Evans, both from the University of Brighton’s School of Computing, Engineering and Mathematics. For Crimtan, the work will fall in line with the company’s commitment to responsible and effective advertising.
Brands looking at new ways to present to audiences can benefit from this type of approach. It might seem like a good idea to pick up the latest technologies but users will soon let them know if they feel their privacy is being violated or if a line of comfort has been crossed with a targeted approach. That could mean a lot of money wasted for brands.
According to the partnership. the AI techniques used will replicate the human intelligence used in online advertising. Crimtan’s data, the company’s online advertising experts’ experience and computer modelling techniques will all be used to enable machines to make the decisions humans would make when faced with new situations.
Accounting for negative actions
An interesting part of the approach is the use of negative modelling techniques. At the moment, online campaign decision-making is governed by user actions like clicks, hover-overs and online purchases. The value of inaction has not really been counted so far.
Negative modelling techniques can help to define decision-making rules by recognising inactions, non-occurances and non-events. Basically a bit like spotting the problems or where the gaps are.
Recognising and counting this inactivity can limit wasted ad displays and give new relevance to online metrics.
Dr Evans is pleased withe the partnership and sees Crimtan as a forward thinking company. He said:
“Advanced mathematics has helped the Internet to evolve into what it is today but there’s a great deal of room for improvement. We will be using advanced mathematics to define logical rules that underlie both predictable and surprising behaviour of Internet users, brands and online advertising experts.”
Paul Goad, CEO of Crimtan also sees the benefit of working with academic experts. He noted that the advertising space is a good match for a scientists working in the field of AI:
“The digital advertising industry is increasingly driven by data, and regulation is growing increasingly severe. Digital marketing needs to evolve and use new techniques and technologies to adapt to customer concerns.”
The program is set to run for two years, that’s a long time in Internet years. No doubt the changes in user habits will need to be incorporated into the research in a dynamic fashion in order to find predictable results that are useful in a practical way.
Whatever the outcome, some top thinkers working in online advertising should not only help the industry more widely, it can also mean that regular folk on the web have a more comfortable experience online.
Image Credit: Brewbooks
Get the TNW newsletter
Get the most important tech news in your inbox each week.