Checklist Colombia AI Olympiad 2025 Problem 1 (round not stated) · Task 1
Heart Disease Risk Prediction
Predict whether a synthetic patient has a high or low five-year heart-disease risk.
The task
A synthetic but realistic dataset, generated in Python with dependencies inspired by the Framingham Heart Study, describes patients by age, gender, smoking, cholesterol and its yearly change, stress level and diet quality. The target heart_disease_risk is 1 (high) or 0 (low); about 40% of records are high risk.
The data contain cascading dependencies (gender affects smoking, smoking affects cholesterol and its change, age affects baseline cholesterol), ordinal categorical variables and overlapping distributions.
Abridged by SOTA from the official materials. The official statement has the exact rules, and it wins wherever this summary differs.
At a glance
- You get
train.csv,test.csvandsample_submission.csv.- You submit
- CSV with columns id and
heart_disease_risk. - Scoring
- F1 score.
- Rules
- Maximum of 10 submissions per day.
- The rules state that entries must be submitted individually.
- Format
- Kaggle competition titled 'Colombian AI Olympiad 2025 (Pr1)'.