ABSTRACT
Conversion optimization means designing a web interface so that as many users as possible take a desired action on it, such as register or purchase. Such design is usually done by hand, testing one change at a time through A/B testing, or a limited number of combinations through multivariate testing, making it possible to evaluate only a small fraction of designs in a vast design space. This paper describes Sentient Ascend, an automatic conversion optimization system that uses evolutionary optimization to create effective web interface designs. Ascend makes it possible to discover and utilize interactions between the design elements that are difficult to identify otherwise. Moreover, evaluation of design candidates is done in parallel online, i.e. with a large number of real users interacting with the system. A case study on an existing media site shows that significant improvements (i.e. over 43%) are possible beyond human design. Ascend can therefore be seen as an approach to massively multivariate conversion optimization, based on a massively parallel interactive evolution.
Supplemental Material
Available for Download
Supplemental material.
- Tim Ash, Rich Page, and Maura Ginty. 2012. Landing Page Optimization: The Definitie Guide to Testing and Tuning for Conversions (second ed.). Wiley, Hoboken, NJ. Google ScholarDigital Library
- Daren C. Brabham. 2013. Crowdsourcing. MIT Press, Cambridge, MA. Google ScholarDigital Library
- Jürgen Branke. 2002. Evolutionary Optimization in Dynamic Environments. Springer, Berlin. Google ScholarDigital Library
- Builtwith. 2017. A/B Testing Usage. (2017). https://trends.builtwith.com/analytics/a-b-testing Retrieved 1/9/2017.Google Scholar
- eMarketer. 2016. US Digital Ad Spending to Surpass TV this Year. (2016). https://www.emarketer.com/Article/US-Digital-Ad-Spending-Surpass-TV-this-Year/1014469 Retrieved 2/1/2017.Google Scholar
- Dario Floreano, Peter Dürr, and Claudio Mattiussi. 2008. Neuroevolution: From Architectures to Learning. Evolutionary Intelligence 1 (2008), 47--62.Google ScholarCross Ref
- Babak Hodjat and Hormoz Shahrzad. 2013. Introducing an Age-Varying Fitness Estimation Function. In Genetic Programming Theory and Practice X, Rick Riolo, Ekaterina Vladislavleva, Marylyn D Ritchie, and Jason H. Moore (Eds.). Springer, New York, 59--71.Google Scholar
- Ron Kohavi and Roger Longbotham. 2016. Online Controlled Experiments and A/B Tests. In Encyclopedia of Machine Learning and Data Mining, Claude Sammut and Geoffrey I. Webb (Eds.). Springer, New York.Google Scholar
- Joel Lehman and Risto Miikkulainen. 2013. Boosting Interactive Evolution using Human Computation Markets. In Proceedings of the 2nd International Conference on the Theory and Practice of Natural Computation. Springer, Berlin.Google ScholarCross Ref
- Joel Lehman and Risto Miikkulainen. 2013. Neuroevolution. Scholarpedia 8, 6 (2013), 30977. http://nn.cs.utexas.edu/?lehman:scholarpedia13Google ScholarCross Ref
- Khalid Salehd and Ayat Shukairy. 2011. Conversion Optimization: The Art and Science of Converting Prospects to Customers. O'Reilly Media, Inc., Sebastopol, CA.Google Scholar
- Jimmy Secretan, Nicholas Beato, David B. D'Ambrosio, Adelein Rodriguez, Adam Campbell, J. T. Folsom-Kovarik, and Kenneth O. Stanley. 2011. Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space. Evolutionary Computation 19 (2011), 345--371. Google ScholarDigital Library
- Sentient Technologies 2017. It's not A/B, I's AI. (2017). http://www.sentient.ai/ascend Retrieved 1/9/2017.Google Scholar
- Hormoz Shahrzad, Babak Hodjat, and Risto Miikkulainen. 2016. Estimating the Advantage of Age-Layering in Evolutionary Algorithms. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2016). ACM, New York, NY, USA. Google ScholarDigital Library
- H. Takagi. 2001. Interactive Evolutionary Computation: Fusion of the Capacities of EC Optimization and Human Evaluation. Proc. IEEE 89, 9 (2001), 1275--1296. http://ieeexplore.ieee.org/iel5/5/20546/00949485.pdf?tp=&arnumber=949485&isnumber=20546Google ScholarCross Ref
- Daniel Yankelovich and David Meer. 2006. Rediscovering Market Segmentation. Harvard Business Review 84, 2 (2006).Google Scholar
Index Terms
- Conversion rate optimization through evolutionary computation
Recommendations
Gamified educational website conversion optimization
TEEM '14: Proceedings of the Second International Conference on Technological Ecosystems for Enhancing MulticulturalityIn this paper, we proposed novel approach to e-learning website conversion optimization using gamification. Analysis of current website analytics has identified several gaps between expected and present state. We used traditional three-stage conversion ...
The impact of interactive design as a conversion rate optimisation tool for e-commerce
This research focuses on a serious issue with regards to low conversion rates (CR) in e-commerce websites. It investigates the phenomena in a series of phases using an e-commerce website as the case study. The A/B testing framework was used to investigate ...
Effects of training and representational characteristics in icon design
Icons are a very important component of graphical user interfaces. However, icon design is still predominantly artistic in nature and as a result icon selection is generally based on usability evaluations after a set of alternative icons are developed. ...
Comments