The online retail sector is the main driver of growth in European and North American retailing, achieving in Europe growth rates of 18.4% (2014), 18.6% (2015) and expected rates of 16.7% (2016) and 15.7% (2017). In comparison, the annual growth rates for all types of retailing range between 1.5% and 3.5% pa. The key metric of e-commerce effectiveness is ‘Customer Lifetime Value’ which calculates the mean revenue per customer over a defined period of time. A 2015 survey by RJMetrics showed a mean CLV-365 of $154. The aim of the Dynamic Automated Predicted Segmentation is to apply Machine Learning algorithms to improve the average CLV uplift to 30% when compared to the capabilities of existing (average +5%) best-in-class product recommendation techniques. If such uplift is achieved, then customers will ultimately see revenues lifted in excess of this as a result of the collateral referral and brand kudos benefits. The benefits from this unique approach are that Customers/Clients of the Merchandising Platform will: a) Receive increased revenues from each consumer, get a better purchasing experience for each consumer and make better use of their product range thereby reduce stock requirements/costs; b) Reduce consumer’s wasted time, working through irrelevant information and so have a higher repurchase frequency; and c) Experience increased consumer loyalty and referral rates, improving the cost effectiveness of customer acquisition activities ultimately resulting in more rapid growth in active customer base and improved competitor differentiation.