Methods for multi-output regression
Description
In this project, a group of students will explore the state of the art on multi-output regression methods. The students should choose at least two regression families such as kernel methods, tree methods, variants of svm regression, etc, identify promising multi-output methodologies and justify their choice in a written report. They will then proceed to implement at least two of them and evaluate them on various data sets
Objective
- Understanding of multi-output methods
- Implementation in a real-world data set
- Sharpen development skills in Python
Data sets
- http://archive.ics.uci.edu/ml/datasets/Solar+Flare
- https://www.kaggle.com/c/online-sales
- https://www.kaggle.com/c/mercari-price-suggestion-challenge
- Private dataset will be shared individually
Target audience
Ideal for students seeking to understand regression methods better and apply the state of the art