CS 570 Projects

Assigned:Monday March 3
Proposal Deadline:Monday March 31, 11:59pm
Final Project Deadline:Monday April 28, 11:59pm

Those of you enrolled in CS 570, the graduate version of Artificial Intelligence, have an additional assignment: an independent project. There are roughly 16 of you.

You need to submit a proposal by March 31st, which must be approved. Your completed project is due April 28th. The proposal is submitted via canvas. The project itself, including code files, will be submitted via gradescope.

I need proof that your program actually runs. The best proof would be that I can run your code on the zoo, without lots of other software updates. You could also have a standalone website that demonstrates your code. Note: not a website / server that I have to install. In the spirit of belt and suspenders, you should also have evidence in the form of a transcript, jupyter notebook file (including HTML and/or PDF), and even a video showing your program in action. If I can't verify your project, you automatically lose 10%.

We encourage you to propose something that interests you. Below are some ideas that may stimulate your thought process.

CS 570 Project Suggestions

  • Emotions applied to an AI system.

  • Recommendation system. Smart search, like a reference librarian who understands your goals.

  • Qualitative arithmetic (When is a number a "good number" or a "bad number"?)

  • Qualitative pre/post analysis for quantitative analysis. (Pre: Why perform test? Why use this data? / Post: what is the meaning of the results? what action should I take? should I perform additional tests?) An AI system that can explain itself.

  • Build a rule base expert system.

  • Finance application: equity analysis, risk management, big data

    Example: Create a risk management system for equity portfolios. Given a portfolio of US or international stocks, across the capital spectrum (large, mid, small), create a system that will calculate a 5 day value at risk (VAR) at the 95% level. Also, perform stress tests and scenario analyses using both historical data and prospective scenarios. For international stocks, include foreign exchange (FX) risk analysis. The system should produce a summary heat map analysis (Green, Yellow, Red) indicating the risk level of the portfolio. Extra credit: if the portfolio is in the red range, the system can suggest trades that would mitigate the risk.

  • Monte Carlo simulation a la hw3

  • Machine Learning: you may use other packages, such as, sci kit learn, pytorch, TensorFlow.

  • Build out a project from one of the Norvig modules, e.g.,

  • Moral reasoning: a program that reasons about ethics, morality, even religion. It can complement or implement your final paper.

  • Build a robot.

    If you want to use a language other than Python, you need prior approval.