About the challenge
This hackathon challenges participants to apply data science and machine learning to combat fraud in energy consumption. With the increasing demand for energy, fraudulent activities such as meter tampering, energy theft, and inaccurate billing have become significant concerns. This competition seeks innovative solutions to detect anomalies in electricity and gas consumption data, ensuring fair energy distribution and cost management.
Get started
To kickstart the hackathon, download the dataset and relevant files using the link below:
https://drive.google.com/drive/folders/1npnp3a_-dTwGmXKffsAmybV6tDP4Gob6?usp=sharing
Make sure to review the provided instructions and familiarize yourself with the data before starting. If you encounter any issues, feel free to reach out for support. Happy hacking!
Requirements
What to Build
Participants are required to build a machine learning model that predicts fraudulent electricity or gas consumption. The solution should leverage the dataset provided to identify anomalies and classify consumption behaviors effectively.
What to Submit
The submission file should be a CSV with the following structure:
- Columns:
- client_id: Unique identifier for each client in the test dataset.
- target: Predicted probability of fraud (values between 0 and 1).
Prizes
SWAGS AND CERTIFICATIONS
Devpost Achievements
Submitting to this hackathon could earn you:
Judges
dsaic-dekut
DSAIC
Judging Criteria
-
Evaluation Metric
Your submission will be evaluated based on the Area Under the Curve (AUC), so ensure your predictions are accurate.
Questions? Email the hackathon manager
Tell your friends
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.