5 Steps to Tackle Real-World Imbalanced Data

Author(s): Snehal Nair

Originally published on Towards AI.

Baseline Model without resampling

Working with imbalanced data can be very challenging. Imbalanced data refers to data where classes do not have equal weight. Some examples of imbalanced datasets include fraud detection, churn prediction, real-time bidding, etc., where over 95% of the data belongs to one class. Tackling such a dataset that can meet both models’ optimizing and gating metrics can be daunting.

source: unsplash @Maksym Sirman

Recently, I got curious about real-time bidding (RTB) in programmatic advertising. RTB is a means by which ad slots on a web page or app are bought by bidders, i.e., advertisers( who are also called DSP — Demand Side… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI