Challenge

Intuit QuickBooks markets new products, training, and other services through email, both to current customers and potential customers. Email lists are precious resources since recipients can easily unsubscribe at any time. In order to ensure the effectiveness of marketing, retention, and customer service efforts, it is important to assess the ideal email cadence for each individual on the list.

Solution

Intuit QuickBooks engaged Evolytics to build and productionize a Recency Frequency Model (RFM) using machine learning techniques to predict the perfect time to send an email message to a current or prospective customer. 

This real-time data science insight is added as a marketing segmentation tool within the marketing email environment, allowing users to build campaigns and set the desired cadence for a particular campaign.

Results

Marketing professionals on the QuickBooks team can determine the best course of action regarding the timing of their campaign sends, with visibility into the predicted outcome for every recipient. In this way, the Evolytics Data Science team created a predictive machine learning model that serves segmentation and forecast needs, reducing the need for guesswork on how to time a particular campaign.

Related A/B Testing Blog Posts

A/B testing and experimentation insights and best practices.

How to Analyze Inconclusive A/B Test Results
How to Analyze Inconclusive A/B Test Results

It’s all fun and games until your A/B Test is flat-tastic. Unfortunately, the ideal isn’t always real, and inconclusive A/B…

How to Run A/B Tests with Small Sample Sizes
How to Run A/B Tests with Small Sample Sizes

Successful digital optimization programs don’t need unlimited traffic. How to deal with small sample sizes is one of the most…

Experiment Nation features Evolytics’ Kenya Davis
Experiment Nation features Evolytics’ Kenya Davis

Kenya Davis, Senior Manager of Decision Science, was featured in “A Panel Conversation on Experimentation Program Goals” Experiment Nation‘s mission?…

Building a Better A/B Testing Process
Building a Better A/B Testing Process

A strategy for building successful experimentation programs Leading digital experimentation tools such as Optimizely, Adobe Target, Google Optimize, Split IO, and…