Competition Rules: Facebook Ad Campaign Budget Prediction

Objective:

Develop a machine learning model to predict the budget required for a Facebook advertising campaign based on provided historical data.
Data:

Participants will be provided with a training dataset containing information on ad creatives, targeting parameters, ad performance metrics, and actual budget spent.
Submission Format:

Submissions must be in CSV format.
Each submission should include Ad_ID and the corresponding Predicted_Budget column.
Evaluation:

Submissions will be evaluated based on the accuracy of the predicted budgets compared to the actual budgets.
The evaluation metric will be Mean Absolute Error (MAE).
Model Training:

Participants are free to use any machine learning algorithms or frameworks.
Overfitting to the specific training dataset is discouraged.
Data Usage:

Participants should only use the provided training dataset for model training.
External data sources are not allowed.
Team Size:

Teams can have a maximum of 3 members.
Code Submission:

Participants must submit the code used to train their models.
The code should be well-documented for reproducibility.
Prizes:

Cash prizes will be awarded to the top-performing teams.
Recognition on the Kaggle platform and social media.
Timeline:

The competition will have a defined start and end date.
Late submissions may not be considered.
Code of Conduct:

Participants are expected to follow Kaggle's code of conduct.
Plagiarism and any form of cheating will result in disqualification.
Organizer's Decision:

The organizer's decision on winners and rule interpretation is final.
By participating in the competition, participants agree to abide by these rules. The rules may be subject to updates or changes, and participants should regularly check for any announcements or clarifications from the organizers.