CS7646 Spring 2017

Overview

You are on the page for information specific to the Spring 2017 session of this course. Go here (Machine_Learning_for_Trading_Course) for overall course policies.

2017 Spring Schedule

• [[1]]

Assignments & Grading

Projects (70%)

• [MC1-Project-1: Assess portfolio] 5% (easy)
• [MC1-Project-2: Optimize a portfolio] 5% (easy)
• [MC2-Project-1: Build a market simulator] 10% (moderate)
• [MC3-Project-1: Implement and assess a regression learner using decision trees and random forests] 15% (hard)
• [MC3-Project-2: Q-learning maze navigation] 10% (easy)
• [MC3-Project-3: Implement a "manual" quant strategy, then do it with decision tree classification] 15% (very hard)
• [MC3-Project-4: Q-learning trader] 10% (moderate)

Extra credit project

If you choose to do the extra credit project, you can gain up to 15 additional points applied to the Projects portion of the class. In this case total projects grade is calculated as

min(70, sum(project grades) + extra credit grade)

Accordingly, you don't need to complete the extra credit project to earn a perfect projects score. We strongly recommend that you focus on the first 7 projects only and skip the extra credit one. However, if you bomb one of the other projects, if you want to challenge yourself, or if you need to make up points you can attempt VICIOUS RABBIT 2000. Note however that this last project is extremely hard. It has so far only been attempted by senior graduate students and the Black Knight. No one has succeeded to date.

• [MC3-Project-5: Q-learning VICIOUS RABBIT 2000] 15% (extremely hard)

Homework (5%):

• [MC3-Homework-1: Generate datasets that defeat learners] 5%

Exams (22%)

• Midterm Study Guide
• Final Study Guide
• Midterm 11%
• Final 11%

Class participation (3%)

• Class participation is determined by activity on piazza.

Thresholds

• A: 90% and above
• B: 80% and above
• C: 70% and above
• D: 60% and above
• F: below 60%

These are hard boundaries (we round down).