Project

The final project can be done in groups of up to two. Students should implement an end-to-end pipeline for a task, use real datasets and process them with different techniques for concepts learned in the class. The students should develop custom solutions for their task, evaluate performance (quality, efficiency, robustness, and scalability) against baselines and document their findings.

The subject of the project is open-ended where students need to do at least the following:

1. implement the end to end data science pipeline for some task
2. explore the different techniques for concepts learned in the class and qualitatively evaluate their need for this task
3. develop a customized solution for the application
4. empirically evaluate the performance (quality, efficiency, robustness) of the developed system and compare with baseline techniques
5. [Optional] Build a demo or easy to use library