Enhancing Sales Meeting Analysis with Advanced LLM-powered Pipeline
Telecom
About the project
The Client was struggling with growing customer churn, which was their biggest problem, and they couldn’t prevent it due to multiple factors, including ineffective customer retention strategy, lack of essential information, and too long feedback loop.
Our tasks
Churn prediction & reduction
Creating a 360 view of each customer along with predictive models enhancing 360-view with churn predictions.
Enabling product recommendation
Deploying predictive models enhancing 360-view with product recommendations.
Delivering suggestions
Developing tools delivering suggestions on how to take care of churn-prone customers to front-line employees.
Integrating models
Integrating created models with client’s systems.
Updating models regularly
Keeping track of feedback loop to keep predictive models up to date.
01
Challenges
1. Ineffective company retention strategy
2. Lack of data on churning customers
3. No data-driven strategy for churn reduction
02
Solutions
Technology we used
AWS Lambda
AWS SQS
Azure ML
Mongo DB
Python
03
Project Results
10x return on ROI
During the pilot, we were able to beat the goals almost twice, saving our client over $39k every month and much more than that after rollout – and that is not taking into account the cost of acquiring customers in place of those that left for competition. After full system rollout, our client ended up with more than 10x return on their investment.
Adopting custom-centric culture
The focus on the customer instead of the abstract concept of Revenue Generating Unit clarifies how the company as a whole is perceived by customers; our telecom is no longer looking at “internet numbers” separately from “tv numbers”. It’s important to realize that for a customer it doesn’t matter what department they work with, if they’ve had bad experiences with one service, they aren’t likely to choose another one from the same provider.
Company-wide AI implementation
Artificial Intelligence was implemented company-wide. Predictions using machine learning models are used not only in sales & retention but also in other departments, for example, to determine which pieces of infrastructure should be upgraded to prevent churn. What’s more, new models can be introduced by the client’s employees themselves.
Improving project management practices
We introduced Agile & DevOps practices in our client’s organization which proved to be a successful way to run the project in their company. During the last couple of years, it was the first IT project for our client that was finished on time and within budget (or actually much before the deadline with some budget left).
Triggering digital transformation company-wide
The good practices from that initiative triggered company-wide transformation as their IT finally got arguments and “green light” for practices they have been trying to introduce and business got the speed of delivery and stability that was desperately needed.
Conclusion
The PoC was successfully introduced and brought significant results – 10x on investment. Therefore, the Client decided to continue with a company-wide introduction of AI doing it on a bigger scale.
