Scribd
Upload
2 views2 pages

Machine Learning Project for UC3M Master's

The project involves using machine learning models to predict two target variables, Y1 and Y2, using a benchmark dataset from UC3M's Master in Big Data Analytics program. Students must implement at least three different scikit-learn models, including a kernel method, and apply preprocessing and hyperparameter selection. Deliverables include a Python notebook and a two-page PDF report detailing the model and results, with evaluation based on code quality, results presentation, and prediction accuracy.

Uploaded by

Ramón García
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views2 pages

Machine Learning Project for UC3M Master's

The project involves using machine learning models to predict two target variables, Y1 and Y2, using a benchmark dataset from UC3M's Master in Big Data Analytics program. Students must implement at least three different scikit-learn models, including a kernel method, and apply preprocessing and hyperparameter selection. Deliverables include a Python notebook and a two-page PDF report detailing the model and results, with evaluation based on code quality, results presentation, and prediction accuracy.

Uploaded by

Ramón García
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Project 1

Machine Learning

Master in Big Data Analytics, UC3M. February 2025.

In this project you are going to work with the benchmark dataset contained in this repository:
[Link]

The web site of the data set provides code to download it and open it in python.

Your goal is to use machine learning models to build predictors for the two target variables
Y1 and Y2 with the following constraints:

●​ Try at least 3 different scikit learn classes of models to decide which one will serve as
final predictor.
●​ At least one of these 3 techniques must be a kernel method.
●​ Use at least a preprocessing method such as scaling, feature selection, etc
●​ At least for one of the stages of the data processing pipeline carry out a
hyperparameter selection.

Deliverable:
Hand in through Aula Global before the deadline:
●​ a python notebook with your code. It must be executed
●​ a 2 pages pdf report explaining your model and discussing the results. Include tables
and/or figures in this report

Evaluation criteria
●​ Clean code with comments and textual explanation of each code block
●​ Tables or figures showing the results
●​ Evaluation the impact of each stage of the data processing pipeline
●​ Quality of the predictions

Evaluation process
●​ I’ll have a meeting with each group and ask you about specific parts of your
code/document during the session.
●​ I will read the report and run the notebook off-line

You might also like