Predictive Shopper is a powerful, predictive intelligence engine that plugs straight into your e-commerce site.

It collects data from lots of sources, including socio-economic, transactional, and online behaviour and predicts precisely, in real time, what a visitor to your site would like to buy.

The output provided is an accurately predicted, personalised communication that helps cross-sell, and upsell, the products most relevant to them.

This delivers intelligent targeting that leads to increased activity, more sales and greater revenue.

DON’T JUST TAKE OUR WORD FOR IT…

Case Study 1:
An online retailer wanted to be more targeted in its communications with their customers.

Using multiple sources of data, Predictive Shopper firstly created a single view, relational database of customers and transactions. Using this data we developed 5 personas based on consistencies in their behaviours.

Using an agreed confidence level of 55% and higher, we were able to identify 8,984 customers that could be targeted with a specific, accurately predicted product where there was a high propensity that they would purchase.

The retailer’s marketing department is currently targeting these customers based on the Predictive Shopper outputs and initial results are showing an increase conversion rate of 30% to date.

Case Study 2:
A national fast food company wanted to show more relevant product offers to its online customers.

Predictive Shopper created a relational database of customers and transactions, whereby one customer had many transactions throughout the timeframe of the data extract.

10 behavioural personas were developed based on the transactional data provided.

Using a confidence level of 70% and higher, we were able to identify 9k customers that could be targeted with a specific, accurately predicted product where there was a high propensity that they would purchase.

515 of these customers purchased the product we presented to them in our popup.

This shows a conversion rate of 5.7% against their previous conversion rate of 2.1%

Case Study 3:
A service provider with multiple retail outlets throughout Ireland wanted to understand where in the country would be the best locations for its next openings.

Using their customer data broken down per outlets, Predictive Intelligence was able to determine the ideal customer for the multiple retailer based on variables such as frequency and average spend.

Once calculated we were then able to layer on demographic data to understand the demographics of this ideal customer.

Predictive Intelligence delivered output data for an interactive map for the next best 5 locations in the country for the multiple retailer to expand to, in order to generate more revenue from its ideal customer