THE PROBLEM
Client, a Fortune-500 FMCG manufacturer, uses Mailchimp to run its B2B email campaigns with the retailers. They were using Mailchimp’s recommendations for identifying the right time to send the emails. However, the client was experiencing very poor open rate (~46%) and click rate (~8%), leading to unsatisfactory sales conversion rate (~3%). Hence, they partnered with Inxite Out with an objective to improve the engagement rates and sales conversion rate of their email campaigns.
INXITE OUT APPROACH
Harmonized Data Lake
A centralized data lake is created to translate the data coming from the different sources (E-commerce, Google Analytics / Google Tag Manager, Email Campaigns etc.) into a harmonized, normalized, unified view which facilitates downstream usage for model development.
Feature Enrichment and Model Development
Curated and enriched the data further with factors such as campaign type, campaign content, brand involved, past behavior of the retailer etc. Leveraged AI to personalize the email content and identify the best time slots to send email campaigns not only for optimizing the open rate and click rate but also for improving the sales conversion rate.
A/B Testing
Finally, model recommendations were validated by running A/B testing on pilot market. Multi-armed bandit approach was used for nimble and efficient decision convergence on A/B testing results.
RESULT
Solution led to a significant (by more than 30%) boost (over Mailchimp’s recommendations) in both open rate and click rate, while generating a ~4% uplift in click-to-open rate in the pilot market consistently during a testing period of 3 months. The sales conversion rate jumped by more than 50% as a result.
