Reducing customer churn by 20% for a large Telecoms provider

Machine Learning | Predictive Models | SaaS | Web Application | Data Science | Design (UI/UX)
Large telecoms provider

Global Pharma Company

Services Provided

Web Applications, AI & ML Modeling, AI Workshop

Project Challenge

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.

Product End Users
  • Broadband Subscribers
  • Customer Success Specialists
  • Telecom Marketing C-Levels
  • Business Analysts

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.


AWS Lambda, AWS SQS, Azure ML, MongoDB, Python

Scope, Custom Software & Data Sources

Educational Content, Interactive Hotspots, Product Training, Interactive Tests & Certification, Voice Over, Sales Enablement

Business Impact Highlights

Increase in drug sales, multi-platform functionality, HoloLens compatible, Framework to rapidly add new drugs




18 months

Data Sources

Customer Historical Data, Social Media Geographical Data, Purchase histories (CRM/ERP)

AI/ML Use cases

User Churn Prediction, Next Best Service


Project Manager, 2 x AI Developer, UX Designer, 2 x Full Stack Developer

The key tasks we needed to solve.

During our initial analysis, the client defined the following tasks to complete.
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.

1. Challenges

1. Ineffective company retention strategy.

The customer retention strategy was based on randomly contacting as many of the customers whose contract would expire in the next couple of months as possible, and giving hefty discounts to the ones that have already canceled their contract. The client had a huge number of product bundles (aka. offers) that were created “just in case”. The number was so high that it was literally impossible for salesforce to learn how to sell the services, and they ended up learning a few selected offers that were the easiest to sell.

3. No data-driven strategy for churn reduction

Many of the employee’s actions were based on guessing and randomly choosing customers to contact or offers to make, so it was difficult to reduce churn, and using the old strategies and techniques made it virtually impossible. Instead of making use of data, they were trying to make use of their intuition. As our client’s employees put it: “We were blind on one-and-a-half eye”.

2. Lack of data on churning customers

The staff was lacking information about which customers were most likely to churn and what the factors impacting such risk were. The feedback loop on how employees’ actions and campaigns affected sales metrics (especially churn) was extremely long; as a result, decisions on who to contact and what should be offered were based on gut feeling of front-line sales force and their managers instead of hard data.

2. Solutions

1.Releasing the models in just 2 months.

We did much better than what had been planned. In just 2 months we released the initial version of 360 view and churn models that we tested on a small sample of customers. That allowed us to optimize those models within 4 months since project inception – initial recommendations for customer retention campaigns based on our solution were available almost half a year earlier than planned.

3. Implementing machine learning company-wide

After additional 2 months of testing a combination of churn prediction and model recommendation, and excellent results (see below), our client decided to roll out our solution for full customer base and introduce machine learning into other departments.

2. Increasing conversion rate by almost x2 times

During the churn model pilot, we trained product recommendation models – that allowed us to increase campaign conversion rates almost twice, not only for churning customers but also for the whole segment.

3. 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.


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.

Looking to implement AI?

Check out our Data Strategy, ArtificiaI Intelligence and Computer Vision workshops

Get started today with a free consult or let us know if you would like to know more about this specific project