Improving the efficiency of online advertising
Our researchers have developed statistical algorithms that inform rapid decisions on deploying adverts to specific online users, resulting in an increase in annual turnover, significant annual savings and an increase in new clients.
More and more companies are having to compete over advertising space in ‘virtual auctions’ due to an increase in real-time bidding. Real-time bidding often happens in the milliseconds that it takes for a webpage to load.
Our researchers in the School of Mathematics have developed statistical algorithms that enable companies to create an overall adaptive bidding strategy for advertising campaigns, informing rapid decisions on deploying adverts to specific online users. Our researcher’s algorithms were adopted by leading digital marketing company Crimtan and have resulted in increased sales estimated at over £3.5m per annum
Research
Researchers Professor Zhigljavsky and Dr Pepelyshev have developed mathematical and statistical algorithms that enable adaptive targeting within website advertisements, helping companies to compete in the process of real-time bidding for advertising space on websites. This allows companies to make faster and more accurate decisions on whether to show a given advert to a particular user using automated real-time bidding.
The research focused on machine learning techniques produced algorithms that identify suitable customers for adverts based on prior online behaviour, and then subsequently devise a bidding strategy when the purchase of an advert is deemed worthwhile.
It also explored the relative influence of factors on clickthrough and conversion rates. The resultant algorithms are able to achieve the same accuracy as computationally demanding machine learning algorithms such as Gradient Boosting or Field-Aware Factorisation Machines (FFM).
The algorithms were well-placed to operate in the split-seconds in which target-advertisement bidding takes place and, via the collaboration with Crimtan, the research was able to quickly impact on the company’s product development and sector competitiveness.
Impact
Increased turnover and new business
The statistical algorithms enabled Crimtan to significantly escalate its programmatic buying strategy and increase the success of its digital marketing campaigns. The research resulted in 20% increased turnover and £2M of new business for the agency. It also enhanced real-time programmatic bidding across Crimtan’s extensive global client base. This increased advert-response rate by 10% and is estimated to have added £3.5M a year in sales to these clients.
Enhancement of Crimtan’s real-time advertising strategy
By incorporating our algorithms into their decision-support products, Crimtan improved the timeliness, efficiency, and accuracy behind online advertisement bidding, and directly reduced their staffing costs. In particular, the automation of the real-time bidding process enabled Crimtan to save £370K annually in associated staff costs, allowing them to rationalise their staffing strategy and reposition some employees into new business areas within the company.
Drawing in international clients
The research has also resulted in Crimtan drawing in additional international clients. The company confirmed that the collaboration has led to the acquisition of £2 million of new business and has increased turnover by 20%.
Meet the team
Publications
Pepelyshev A., Staroselskiy Y., Zhigljavsky, A. and Guchenko, R. (2016) Adaptive targeting in online advertisement: models based on relative influence of factors. Published in: Pardalos, P., Conca, P., Giuffrida, G. and Nicosia, G. (eds.) Machine Learning, Optimization,and Big Data. MOD 2016. Lecture Notes in Computer Science Springer, pp. 159-169.
Pepelyshev A., Staroselskiy Y. and Zhigljavsky, A. (2016) Adaptive designs for optimizing online advertisement campaigns. MODA 11 - Advances in Model-Oriented Design and Analysis. Contributions to Statistics, Springer-Verlag, pp.199-208.
Pepelyshev A., Staroselskiy Y. and Zhigljavsky A. (2015) Adaptive Targeting for Online Advertisement, Machine Learning, Optimization, and Big Data. Springer Lecture Notes in Computer Science, Vol. 9432, pp. 240-251.
Zhigljavsky A., Žilinskas A.G. (2008) Stochastic Global Optimization, Springer-Verlag US.
Zhigljavsky A., Hamilton E. (2010) Stopping rules in k-adaptive global random search algorithms. DOI: 10.1007/s10898-010-9528-6 Journal of Global Optimization, v. 48, No. 1,87–97.
Pepelyshev, A., Zhigljavsky A., and Žilinskas A. Performance of global random search algorithms for large dimensions. Journal of Global Optimization, 71 (2018): 57-71.
