A predictive analytics platform could act as a “crystal ball” for retailers by showing how and where they should spend their online ad budgets.

Forecaster, which comes from online retail specialists Summit, collects data – both internal and external – from a variety of sources such as transaction history, location and weather to predict likely sales from marketing spend.

The technology recommends the best approach for adjusting bid levels and messaging for display, product listing and paid search ads, helping retailers maximise the profit from each channel.

Forecaster, which was developed over four years, has been designed in collaboration with a team of PhD statisticians lead by Durham University’s Professor David Wooff.

Campaign optimisation

The analytics engine was created to answer the questions of Summit’s clients such as how much budget should be spent and in what channel, says Hedley Aylott, Summit’s CEO.

“They want a crystal ball and this is as close as it gets. Predictive analytics is the most sophisticated and accurate form of campaign optimisation available and addresses the age old issue of establishing the correct budget.”

Undeniably, some of the data collected is old-fashioned common sense. Paddling pools are sold when the weather is warmer and sledges fly off the shelves when it snows. That said, retailers who have already used Forecaster have reported positive results.

An Argos campaign which used the platform found an increase in paid search traffic of 33%.

Argos also found that sales rose by 31%, conversion rates by nearly 5% and the average order value by 18%, resulting in the cost of each sale falling 14%.

The platform is available to retailers as part of Summit’s online marketing service or as a stand-alone product for retailers and agencies who manage campaigns in-house.