Artificial Intelligence - Predictive Models / Web Development

Reducing customer churn by more than 20% with 10x ROI

Telecom

Building the AI-based platform with a recommender system for one of the biggest Polish telecoms with almost 1 milion customers.

Introduction

About 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

task icon
Churn prediction & reduction

Creating a 360 view of each customer along with predictive models enhancing 360-view with churn predictions.

task icon
Enabling product recommendation

Deploying predictive models enhancing 360-view with product recommendations.

task icon
Delivering suggestions

Developing tools delivering suggestions on how to take care of churn-prone customers to front-line employees.

task icon
Integrating models

Integrating created models with client’s systems

task icon
Updating models regularly

Keeping track of feedback loop to keep predictive models up to date.

Challenges

01

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.

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.

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”.

Solutions

02

1. Launching a pilot AI project

The pilot was initially scoped for 10 months, including:

  • 360 view of each customer,
  • predictive models enhancing 360-view with churn prediction
  • predictive models enhancing 360-view with product recommendations,
  • tools delivering suggestions on how to take care of churn-prone
  • customers to front-line employees,
  • integrations with client’s systems,
  • feedback loop to keep predictive models up to date. After that time, we expected to have initial results on how our solution helped with churn reduction in initially selected customer segments.
2. 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. 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.

4. 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.

Technology we used

AWS Lambda
AWS SQS
Azure ML
Mongo DB
Python

Project Results

03

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.

Do you like our work?

Let's talk

about your project!

Download now!

Enter your personal and working information.

Fill out the form below to watch the recording.

Download now!

Enter your personal and working information.

Fill out the form below to watch the recording.

Fill out the form below to watch the recording and download the infopack.

AI in e-commerce - Greg Gwozdz

Fill out the form below to watch the recording.

Webinar on demand

Enter your personal and working information.

Web development outsourcing poland

Download now!

Enter your personal and working information.