Predicting the Beats-per-Minute of Songs

Overview

This Kaggle competition challenges you to predict a song's beats-per-minute (BPM) using a dataset of song features. It's part of the 2025 Playground Series, designed to help you practice and improve your machine learning skills with an approachable, synthetically generated dataset. Your goal is to build a model that accurately estimates the BPM for a given song.

Requirements

You need to submit a file with two columns: 'ID' and 'BeatsPerMinute'. For each 'id' in the test set, predict the continuous 'BeatsPerMinute' value. The dataset is synthetically generated from real-world data. The competition runs from September 1, 2025, to September 30, 2025, with all deadlines at 11:59 PM UTC.

Prizes

The top three participants will receive Kaggle merchandise. Kaggle merchandise is awarded only once per person in this series, so if you've won before, the prize will go to the next team.