Redefining Customer Engagement by Operationalizing Machine Learning | HCLTech

An Australian multinational bank with businesses across New Zealand, Asia, the United States and the United Kingdom depended on a legacy system to trigger the Next Best Conversation with their customers, which was resulting in less conversion and increased churn rate. To improve customer retention, the client wanted to leverage Machine learning models to predict the likelihood of customers to opt for new business products and suggest appropriate next steps with their customers. Furthermore, the customer also aspired to develop Machine Learning models using MLOps practices for Continuous Delivery and Machine Learning automation pipelines to bring down the lead time of taking models from experimentation to deployment and improve governance.

HCLTech partnered with the client to undertake a significant data and analytics transformation with a focus on deploying and scaling ML models for greater customer conversion. Our approach involved creating a feature store, leveraging auto ML to reduce time for model training, developing an explainable AI module and much more. It resulted in 66% increase in conversion rates from Next Best Conversation and reducing model development and deployment cycle from 4-5 months to six weeks. Download the case study to know more.