Difference between revisions of "CS4646 Spring 2018"

From Quantitative Analysis Software Courses
Jump to navigation Jump to search
 
(15 intermediate revisions by the same user not shown)
Line 1: Line 1:
==DRAFT==
+
==Undergraduate Syllabus==
  
This page is still in progressDon't consider it final until the first day of class.
+
Note that you are on the syllabus page for the '''undergraduate on-campus''' MLT class, CS 4646This syllabus ''does not apply'' to the graduate class, CS 7646.
  
 
==Overview==
 
==Overview==
Line 11: Line 11:
 
* Forum: https://piazza.com/class/jby8m47v3v52oc (just search for CS 4646 if this doesn't work)
 
* Forum: https://piazza.com/class/jby8m47v3v52oc (just search for CS 4646 if this doesn't work)
  
* Schedule:
+
* Project Deadlines: '''All projects are due Sunday night at 11:55 PM Eastern US Time'''.  Projects are due at the '''end''' of the week in which they are listed.  For example, Project 1 (assess a portfolio) is listed as due in Week 3, meaning Sunday 1/28 -- the Sunday ''after'' Week 3.
 +
 
 +
* Late Projects: As stated in class, projects will be accepted up to 24 hours late without any excuse required.  Projects one second to 24 hours late will receive a -10 penalty.  After 24 hours, late projects will not be accepted for any credit at all ''unless'' arrangements were made with the instructor prior to the project deadline.
 +
 
 +
* Schedule: Subject to Change if necessary.  I will give you as much notice as possible.
 +
 
 +
* Exams: Exams are on '''Thursday''' so I can do some review on Tuesday.
  
  
 
{| class="wikitable"
 
{| class="wikitable"
! Week !! Tuesday Class Date !! Topic !! Due
+
! Week !! Date (Tues) !! Weekly Topics !! Due
 
|-
 
|-
|1 || 1/9 || Course Overview, Intro to Markets, Intro to Machine Learning, Pandas Tutorial ||
+
|1 || 1/9 || Course Overview, Python/Pandas Tutorial ||
 
|-
 
|-
|2 || 1/16 || Visualizing Market Data, Pricing Stocks, Numpy Tutorial, Working with Time Series ||  
+
|2 || 1/16 || Numpy Tutorial, Visualizing Market Data, Working with Time Series, Incomplete Data ||  
 
|-
 
|-
|3 || 1/23 || Incomplete Data, Plots, ML Lexicon/Taxonomy, Evaluating Learners ||MC1-P1
+
|3 || 1/23 || ML Lexicon/Taxonomy, Evaluating Learners || Project 1
 
|-
 
|-
|4 || 1/30 || Supervised Learning (KNN, LinReg, Decision Trees, Boosting, Bagging) ||
+
|4 || 1/30 || Supervised Learning (KNN, LinReg, Decision Trees) ||
 
|-
 
|-
|5 || 2/6 || Market History, Actors, Order Book, Order Types ||MC3-P1 + MC3-HW1
+
|5 || 2/6 || Ensembles (Bagging, Boosting), Market History, Actors || Project 2
 
|-
 
|-
|6 || 2/13 || Markets, Valuation, Capitalization, Time Value of Money ||Exam 1
+
|6 || 2/13 || Order Types, Order Book, Leverage ||
 
|-
 
|-
|7 || 2/20 || Options, Leverage ||MC2-P1
+
|7 || 2/20 || Valuation, Technical Analysis, Candlestick Chart Patterns || Project 3
 
|-
 
|-
|8 || 2/27 || Technical Analysis, Candlestick Chart Patterns,  CAPM, Efficient Market Hypothesis ||
+
|8 || 2/27 || Time Value of Money, CAPM, Efficient Market Hypothesis ||  
 
|-
 
|-
|9 || 3/6 || Fund. Law of APM, Efficient Frontier, Finite Automata, Markov Decision Processes ||MC3-P2
+
|9 || 3/6 || Fund. Law of APM, Efficient Frontier, Review || Exam 1
 
|-
 
|-
|10 || 3/13 || Value Iteration, Q-Learning || Exam 2
+
|10 || 3/13 || Finite Automata, MDP, Value/Policy Iteration, '''Drop Day (3/14)''' || Project 4
 
|-
 
|-
|11 || 3/20 || Final class, extra topics ||Final project (MC3-P3)
+
|11 || 3/20 || SPRING BREAK ||
 
|-
 
|-
|12 || 3/27 || Final class, extra topics ||Final project (MC3-P3)
+
|12 || 3/27 || Q-Learning ||
 
|-
 
|-
|13 || 4/3 || Final class, extra topics ||Final project (MC3-P3)
+
|13 || 4/3 || Q-Learning, Misc ML Topics or Catch-up || Project 5
 
|-
 
|-
|14 || 4/10 || Final class, extra topics ||Final project (MC3-P3)
+
|14 || 4/10 || Options, Time Series Q-Learning ||
 
|-
 
|-
|15 || 4/17 || Final class, extra topics ||Final project (MC3-P3)
+
|15 || 4/17 || Review, Exam 2, Last regular day of class || Exam 2
 
|-
 
|-
|16 || 4/24 || Final class, extra topics ||Final project (MC3-P3)
+
|16 || 4/24 || Final Instruction Days (Tuesday), Help Session on Final Project || Project 6
 
|-
 
|-
|17 || 5/1 || Final class, extra topics ||Final project (MC3-P3)
+
|17 || 5/1 || Finals week, NO FINAL EXAM ||
 
|}
 
|}
  
Line 56: Line 62:
 
'''Projects (60%)'''
 
'''Projects (60%)'''
 
* [[http://quantsoftware.gatech.edu/CS4646_assess_portfolio assess_portfolio]] 5% (easy)
 
* [[http://quantsoftware.gatech.edu/CS4646_assess_portfolio assess_portfolio]] 5% (easy)
* Regression / Ensemble Learners 10% (challenging)
+
* [[http://quantsoftware.gatech.edu/CS4646_assess_learners assess_learners]] 10% (challenging)
* Market Simulator 10% (moderate)
+
* [[http://quantsoftware.gatech.edu/CS4646_marketsim marketsim]] 10% (moderate)
* Manual Strategy 10% (moderate)
+
* [[http://quantsoftware.gatech.edu/CS4646_manual_strategy manual_strategy]] 10% (moderate)
* Q-Learning Robot 10% (moderate)
+
* [[http://quantsoftware.gatech.edu/CS4646_qlearning_robot qlearning_robot]] 10% (moderate)
* Strategy Learner 15% (very challenging)
+
* [[http://quantsoftware.gatech.edu/CS4646_strategy_learner strategy_learner]] 15% (very challenging)
  
 
'''Exams (40%)'''
 
'''Exams (40%)'''
Line 66: Line 72:
 
* Exam 2: 20%
 
* Exam 2: 20%
  
'''Exam Study Guides'''
+
'''Please see Piazza for exam study information'''
* [[Midterm Study Guide]]
 
* [[Exam 2 Study Guide]]
 
  
 
==Thresholds==
 
==Thresholds==

Latest revision as of 14:12, 12 April 2018

Undergraduate Syllabus

Note that you are on the syllabus page for the undergraduate on-campus MLT class, CS 4646. This syllabus does not apply to the graduate class, CS 7646.

Overview

You are on the page for information specific to the Spring 2018 session of CS 4646. Go here (Undergrad_ML4T) for overall course policies.

Schedule & Forum

  • Project Deadlines: All projects are due Sunday night at 11:55 PM Eastern US Time. Projects are due at the end of the week in which they are listed. For example, Project 1 (assess a portfolio) is listed as due in Week 3, meaning Sunday 1/28 -- the Sunday after Week 3.
  • Late Projects: As stated in class, projects will be accepted up to 24 hours late without any excuse required. Projects one second to 24 hours late will receive a -10 penalty. After 24 hours, late projects will not be accepted for any credit at all unless arrangements were made with the instructor prior to the project deadline.
  • Schedule: Subject to Change if necessary. I will give you as much notice as possible.
  • Exams: Exams are on Thursday so I can do some review on Tuesday.


Week Date (Tues) Weekly Topics Due
1 1/9 Course Overview, Python/Pandas Tutorial
2 1/16 Numpy Tutorial, Visualizing Market Data, Working with Time Series, Incomplete Data
3 1/23 ML Lexicon/Taxonomy, Evaluating Learners Project 1
4 1/30 Supervised Learning (KNN, LinReg, Decision Trees)
5 2/6 Ensembles (Bagging, Boosting), Market History, Actors Project 2
6 2/13 Order Types, Order Book, Leverage
7 2/20 Valuation, Technical Analysis, Candlestick Chart Patterns Project 3
8 2/27 Time Value of Money, CAPM, Efficient Market Hypothesis
9 3/6 Fund. Law of APM, Efficient Frontier, Review Exam 1
10 3/13 Finite Automata, MDP, Value/Policy Iteration, Drop Day (3/14) Project 4
11 3/20 SPRING BREAK
12 3/27 Q-Learning
13 4/3 Q-Learning, Misc ML Topics or Catch-up Project 5
14 4/10 Options, Time Series Q-Learning
15 4/17 Review, Exam 2, Last regular day of class Exam 2
16 4/24 Final Instruction Days (Tuesday), Help Session on Final Project Project 6
17 5/1 Finals week, NO FINAL EXAM

Assignments

Projects (60%)

Exams (40%)

  • Exam 1: 20%
  • Exam 2: 20%

Please see Piazza for exam study information

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).