Skip to content

Latest commit

 

History

History
60 lines (46 loc) · 2.86 KB

proj.md

File metadata and controls

60 lines (46 loc) · 2.86 KB

Project

We have spent the semester getting familiar with multiple topics in data mining. Some topics were practical (e.g., how do we pick k for clustering) and some were algorithmic (e.g., what is the I/O complexity of various algorithms). Now, it is your time to do something with all these new ideas.

You and a partner(s) get to define and drive the direction of the project. Note that it does not have to be research, but it should be at the very least something that, if successful, you can point to it in a job interview as a substantial project. You may be in groups of up to four. You do NOT need to work with the same people as the topic presentation. The project is intentionally open ended but some places to help you get started are:

  • read and implement a paper
  • build a system that solves some problem that you find interesting.
  • work on a feature of an open source project
  • improve a data mining algorithm
  • come up with an algorithm for extracting insights for a large data set.

Deliverables

For the final project, there will be 3 deliverables described in the sections below. Proposal (Due Multiple Dates) Since each project is self defined the proposal will be in two parts.

  • Written proposal (Due Nov 2). You should submit a one page max description of what you would like to pursue for your project. It should clearly state the problem that you are interested in working on and propose some direction for how you are going to go about solving it. References and figures do not count against your 1 page limit.

  • Proposal discussion (Due Nov 6). Schedule at 20 min to meeting with me on Nov 2-6 to discuss your project. At the meeting we will nail down the scope of work for the project and finalize the expected outcome of your project. It is your responsibility to schedule a time with me. Note that my schedule is pretty full, so we may need to meet outside of the normal 9-5 business hours.

  • Writeup (Due Nov 23) You should submit a five page max writeup of your project. The writeup should clearly describe the problem you are working on, relevant background information, your solution, and any other interesting content that you would like to share with me about your project. Since each project may be very different in what it is doing, the writeups may be very different. We will discuss further details for the writeup during the proposal discussion.

  • Presentation (Due Nov 23) I want you have a project that you are proud of, so, the presentation is your time to shine. We will use the exam period for your presentations. Feel free to get creative. Like the writeup, your presentation will be vary depending on what you are working on. We will discuss further details for the presentation during the proposal discussion.

Grading

The project will be graded as:

  • Proposal (20 points)
  • Writeup (40 points)
  • Presentation (40 points)