INside Performance Marketing
New Tool Adopts Mathematics to Calculate Content’s ROI
Image Credit  João Trindade Creative Commons license

New Tool Adopts Mathematics to Calculate Content’s ROI

Online retailers can now identify which piece of content is driving the most revenue thanks to a new tool from machine-learning analytics platform MathSight.

Utilising a combination of machine learning and data science, Content STAT can pinpoint articles that are showing actual revenue benefits to an e-commerce business whilst highlighting pieces that are not working as hard as they should be.

MathSight is so self assured in Content STAT’s ability that the company says it can determine the web pages driving the most revenue per visitor to a 95% or higher statistical confidence level.

Deeper than web pages

Content STAT goes to work beyond the web pages, too. With the tool’s mathematical clustering techniques it can drill down into what actually points consumers in the direction of the checkout, according to MathSight’s managing director, Andreas Voniatis.

“We can identify the actual attributes of web content that drive increases in revenue,”  Voniatis said. “This could be anything from the number of images, the number of reviews, the average review rating, the price points.

“As long as there are enough visitors and the content is on the page - we'll find it.”

The next step for retailers would be to take the elements that work well and then roll those out across the rest of the website to boost sales and maximise ROI.

Avoiding a lab experiment

While this all has a similar feel to A/B testing, Voniatis says it might be preferential for larger brands that are unwilling to turn large parts of their websites into an exercise in trial and error.

“We’ve all heard of multivariate and split testing, but the reality is nobody wants to expose their business as a living experiment or worse wait six months to see which experiment produced the best outcome,” Voniatis explained.

While the program has been designed with online retailers in mind, its designers have garnered inspiration from a rich pool of sources. Some of the methods used in Content STAT to analyse brands’ big data are said to be similar to those already entrenched in other industries such as Formula One and oil exploration.

Continue the conversation

Got a question or comment – tweet Simon simonnholland or comment on Twitter, Facebook or LinkedIN.

Simon Holland

Simon Holland

Simon is the news and research reporter at Existem. Previously a technology journalist, he now spends his time investigating both future and developing trends in performance marketing whilst producing editorial content for performancein.com

Read more from Simon

Related Articles

Join over 10,000 performance marketers for the ultimate weekly update on industry news