At [Spacewalk](https://www.spacewalk.tech/), our models deal with **geometries** a lot.

But it's **not trivial** for a NN to learn a **good representation** (good features) of the input geometries.
And if the geometry is not well-represented, it **directly impacts the quality** of the results.

---

In this competition, you will train a NN to learn good representation by training the model to predict various properties of the given polygon, such as: 
* **Area**
* **Perimeter**
* **Size** (on the x-axis and the y-axis)
* **Concavity** (concavity is a **ratio** that represents *how much concave a polygon is*)
* **Minimum clearance** (minimum clearance is **smallest distance** by which a point could be moved to produce an **invalid** geometry)
* **Centroid**
* **OMBR ratio** : (Oriented Minimum Bounding Rectangle ratio, representing *how close the polygon is to a rectangle*)
* **OMBR Aspect ratio** (represents the wideness of the polygon)
* **Opening ratio** (represents the ratio of deadspace (not wide enough) of the polygon)

---

📢 ***If you are reaching interesting results, [Spacewalk](https://www.spacewalk.tech/) is definitely interested in your profile for an ML engineer position! Please share your results through the [Discussion panel](https://www.kaggle.com/c/cartesius/discussion).***