## About the Domain
Online learning platforms, such as DataCamp, provide thousands of courses covering programming, data science, and machine learning. Each course is designed with metadata that captures its structure, topic, difficulty, and learner engagement. Understanding which factors influence course quality can help platforms improve content and optimize learning experiences.

## Competition Details
In this competition, your goal is to predict the **average rating of a course** (`course_rating`) based on its metadata. This is a **regression problem**, where higher ratings indicate greater learner satisfaction.

The dataset is split into three files for this competition:
`train.csv` – Contains course metadata and the target variable `course_rating` .
`test.csv` – Contains course metadata without`course_rating`; participants must predict it.
`sample__submission.csv` – Template showing the required submission format.

The dataset includes the following features:
- `title` and `description` (text features)
- `difficulty_level` and `programming_language` (categorical features)
- `num_chapters`, `num_exercises`, `num_videos`, `nb_of_subscriptions`, `xp`, `time_needed_in_hours` (numeric features)

Participants are encouraged to explore feature engineering, text processing, and a variety of machine learning models, including linear regression, ensemble methods, and NLP-based approaches on the course text.