RSS feed Get our RSS feed

News by Topic

BizReport : Search Marketing : January 21, 2015

Predictive analytics platform a 'crystal ball' for online ad campaigns

A new predictive analytics platform can tell advertisers how much they should spend, in what online channel and what return they can expect thanks to sophisticated statistical models.

by Helen Leggatt

Online retail specialist Summit has launched a predictive analytics platform that is being dubbed a 'crystal ball'. Called Forecaster, the predictive analytics engine was developed by a team of PhD statisticians led by Professor David Wooff from Durham University.

According to Summit's CEO, Hedley Aylott, "predictive analytics is the most sophisticated and accurate form of campaign optimization available and addresses the age old issue of establishing the correct budget. No more educated guesses and marketing based on preference - in trials with our major retail clients we've seen Forecaster increase margins from campaigns by as much as 900%."

A major feature of Forecaster is the sheer scope of data and buying triggers it uses such as weather, location, transaction history, stock availability and television.


"We 'fingerprint' TV ads by client and their competitors - when a TV ad appears, we instantly make changes to the client's online ads," says Aylott. "For example, PC World advertises a tablet, we increase bids for Argos tablet ads for a set period of time to ensure we capture people who go online to buy after seeing the TV ad."

Marketers can use Forecaster to maximize conversion and optimize marketing campaigns. The predictive analytics platform can reveal patterns in the data such as the effect outside temperature has on sales of such items as lawn mowers and paddling pools, or when search volumes change relative to the airing of a TV ad.

Statistical models are applied to the data to predict likely sales from a given marketing spend. To achieve the predicted sales, Forecaster then recommends how to adjust the bid level and messaging for paid search, display and product listing ads so profit from each channel is maximized.

Using the Forecaster platform, retail store Argos was able to increase paid search traffic by 33%, sales by 31%, lift conversion rates by nearly 5% and raise the average order value by 18%.

Image via Shutterstock

Tags: advertising, analytics, campaign performance, predictive technology, retail, TV

Subscribe to BizReport



Copyright © 1999- BizReport. All rights reserved.
Republication or redistribution of BizReport content is expressly prohibited without the prior written consent.
BizReport shall not be liable for any errors in the content, or for any actions taken in reliance thereon.