Inspiration

In today's age of big data and information, we would like to utilise our skills to optimise customers' satisfaction and enhance service qualities, by handling the available data with integrity and creativity.

What it does

Predicting which customers of SaaS (Software as a Service) businesses are most likely to churn based on customer’s characteristics e.g. demographic, dependency, etc. It may be possible to apply the model to other SaaS businesses as we built this model based of a Telco dataset.

How we built it

We plan to base our model on the variables and data accessed through a Telco Customer Churn dataset to create a logistic regression model to predict customers most likely to churn.

Challenges we ran into

As a first time attempting a comprehensive machine learning project, we met with many unfamiliar aspects of machine learning during the ideation process, but it also exposed us to many new terms that we learned upon research. Writing and researching on how to create the Machine Learning model was especially tough.

Accomplishments that we're proud of

Despite a lack of knowledge on machine learning in the fintech field, we actively engaged in research to learn more about machine learning and use it in our application.

What we learned

We learned about many new machine learning components and their purposes, such as tech stack, ML pipeline, API, etc.

What's next for Reducing Customer Churn by Team 5G

Refining our Machine Learning model.

Built With

Share this project:

Updates