Introduction

In this challenge, you'll get the opportunity to tackle one of the most industry-relevant maching learning problems with a unique dataset that will put your modeling skills to the test. Subscription services are leveraged by companies across many industries, from fitness to video streaming to retail. One of the primary objectives of companies with subscription services is to decrease churn and ensure that users are retained as subscribers. In order to do this efficiently and systematically, many companies employ machine learning to predict which users are at the highest risk of churn, so that proper interventions can be effectively deployed to the right audience.

In this challenge, we will be tackling the retention prediction problem on a very unique and interesting group of subscribers, Coursera learners! On Coursera, learners can subscribe to sets of courses in order to gain full access to graded assignments, hands-on projects, and course completion certificates. One of the most common ways that learners subscribe to content is via Specialization Subscriptions, which give learners unlimited access to the courses in a specific specialization on a month-to-month basis.

Imagine that you are a new data scientist at Coursera and you are tasked with building a model that can predict which existing specialization subscribers will continue their subscriptions for another month. We have provided a dataset that is a sample of subscriptions that were initiated in 2021, all snapshotted at a particular date before the subscription was cancelled. Subscription cancellation can happen for a multitude of reasons, including:

• the learner completes the specialization or reaches their learning goal and no longer needs the subscription
• the learner finds themselves to be too busy and cancels their subscription until a later time
• the learner determines that the specialization is not the best fit for their learning goals, so they cancel and look for something better suited

Regardless the reason, Coursera has a vested interest in understanding the likelihood of each individual learner to retain in their subscription so that resources can be allocated appropriately to support learners across the various stages of their learning journeys. In this challenge, you will use your machine learning toolkit to do just that!