The problem
There is a crowd-sourcing project which is named Galaxy Zoo that people describe morphology of galaxies based on their shapes. There is some questions that form a decision tree to classify the input galaxy into some categories.
Figure 1 shows the decision tree of galaxies.
![](https://storage.googleapis.com/kaggle-media/competitions/inclass/5255/media/Tree.png)
In galaxyzoo website people classified galaxies and their answers can be aggregated into a set of probabilities for each galaxy.
Learning these probabilities helps us to evaluate people's choice accurately.
The goal of this challenge is to predict these probabilities from the training galaxy images. In other words, build a model of how “the crowd” perceive and classify these images.
We face a
regression
problem, not a classification one and we don’t have to determine which classes the galaxies belong to, but rather the fraction of people who would classify them as such.
Note
:
You can can get more familiar with this competition by following the link:
https://www.galaxyzoo.org/