Implementing a Hadoop data lake on Cloudera cluster led to a 6% increase in customer acquisition
A Global Fortune 500 Telecom provider increased net new and upgraded conversions for omnichannel data by replacing the existing analytics model with cost-effective big data-based analytics and dynamically scalable Hadoop data lake.
A US-based telecom provider was looking for an advanced machine learning analytical model to increase their B2B lead generation and improve the effectiveness of their marketing campaigns. The company, third largest in the US, wanted to migrate to a Cloudera-based Hadoop data lake to grow business revenue.
Though the provider already had an analysis mechanism in action, it was not able to increase net new and upgraded conversions for omnichannel data. They wanted an easy-to-use, cost-effective, and scalable analytical tool to understand the pulse of the customer and increase the ROI of their marketing campaigns.
Impetus Technologies Inc. migrated the existing data from RDBMS and external systems like Salesforce and Marketo to create a Hadoop data lake on the Cloudera (CDH) cluster. The data from all these datasets were mined and mapped to enhance product recommendations.
The solution implemented cross-sell/up-sell, continuum, lead-generation, and multi touch-point attribution models to enhance marketing campaign effectiveness. Audit-trail policies were also applied to monitor and handle failovers.
Cloudera (CDH) 5.8.2, Spark, Hive, Oozie, Sqoop, Scala, Shell-script, Java
Security: Used Kerberos on CDH cluster for authentication and authorization
Monitoring: Added email notifications to all the ML models to monitor data ingestion workflows for failovers
Reliability: Tested all ML models and ingestion workflows
Ease of maintenance: The solution can be optimized by tuning the hyper parameters in the property files. No changes in code is required
Documentation: Documented all data-ingestion workflows and ML models, created run book