Speakers:
Customer Churn Prediction with MLflow and Streamlit
Date:
Wednesday, June 4, 2025
Time:
4:15 pm
Summary:
Priyanka will show you how to build an end-to-end customer churn prediction pipeline using MLFlow. She’ll cover every step of the process—from data preprocessing and feature engineering to tracking experiments, building ML pipelines, and training high-performing classification models. The entire workflow will be managed within MLFlow, allowing us to build, track, and deploy pipelines seamlessly. To make predictions accessible, a user-friendly interface using Streamlit for real-time visualization of churn predictions will be developed. This session offers a practical and approachable way to implement customer churn prediction for both beginners and experienced data practitioners.
Should The Data Always Do The Talking?
Date:
Wednesday, June 4, 2025
Time:
4:40 pm
Summary:
Proponents of exploratory data analysis assert that allowing the data to group naturally without any imposed framework is the most robust and unbiased approach for creating valid output. However, in a business setting there may be times when NLP yields results that are unactionable or confusing due to the difference between the traditional semantic meanings and the business use case. Amy and Mark examine the same data under two different frameworks and provide practical guidance on when to let the data do the talking, and when to let the business speak for itself.