Case Study:

Predictive Analytics for Email Campaigns

PNT Marketing Services

The Client

Our customer, PNT Marketing Services, is an award-winning provider of marketing and analytic services to their end-clients. Their clients included national digital marketing agencies and for-profit education firms who needed advanced analytics to support their growing email and online marketing channels. The initial focus with these clients was to improve their lead generation programs with more sophisticated predictive analytics for email campaigns.

“We are extremely pleased with the performance of LityxIQ. We tested and built over a dozen models in a short time and put them into production more quickly than with other available tools.”
– Tony Coretto, Co-CEO, PNT

The Challenge

In order to provide superior analytic support to their clients, PNT sought out a platform that allowed them to quickly and easily create and deploy predictive models. To best complement their existing services teams, the platform needed to be easy to use for business users and not require statistical programming, yet provide powerful, accurate models that they could deploy for their clients. Having found that LityxIQ met these requirements, PNT began to use the Lityx IQ platform to support complex modeling requirements for multiple clients.

The Solution

PNT constructed a data warehouse to track all contacts and a 12-month history of emails sent. Data recorded for each contact included email clicks, opens, and click-throughs, page visit patterns, conversion data, and call center data. Many subsequent metrics were generated from these fields, including RFM-type metrics such as number of contacts made in the last 12 months, time since last contact, and percentage emails clicked in the recent past. All data was brought into LityxIQ to support advanced analytics and modeling efforts.
PNT used PredictIQ to build multiple models in rapid fashion. Separate models were built for different subsets of their clients’ data and for different prospect behaviors. Models were setup to be refreshed on a regular basis to help account for the fast-changing nature of the clients’ email programs and market conditions. The PNT client services team was able to test results from different algorithms and easily control more technical settings without any coding.
PNT constructed a data warehouse to track all contacts and a 12-month history of emails sent. Data recorded for each contact included email clicks, opens, and click-throughs, page visit patterns, conversion data, and call center data. Many subsequent metrics were generated from these fields, including RFM-type metrics such as number of contacts made in the last 12 months, time since last contact, and percentage emails clicked in the recent past. All data was brought into LityxIQ to support advanced analytics and modeling efforts.

The Results

  • 116% increase in click-thru-rate and 57% increase in click-to-lead rate

  • Fast build and deployment of over a dozen predictive models by non-statisticians
  • Weekly database scoring of over 5 million records to support email campaigns

Get Started
with Lityx