MC3-Project-4 - Revision history

Dave: /* Contents of Report */

2017-07-18T17:00:17Z

Contents of Report

2017-07-18T01:39:37Z

Overview

2017-07-18T01:36:29Z

Overview

2017-07-18T01:35:31Z

Overview

2017-07-18T01:22:39Z

Overview

2017-07-18T01:22:19Z

Overview

2017-07-18T01:06:41Z

Updates / FAQs

2017-07-18T01:06:16Z

DRAFT

2017-07-18T00:24:06Z

Contents of Report

2017-07-18T00:18:42Z

Rubric

@@ Line 77: / Line 77: @@
 Write a report describing your system.  The centerpiece of your report should be the description of how you have utilized your learner to determine trades.  Describe the steps you took to frame the trading problem as a learning problem for your learner.
-In the course of creating your learning trading strategy you will probably evaluate a number of different parameters for your learner and your trading strategy.  Choose two of those to look at more carefully.  Conduct and report on two experiments that illustrate the methods by which you refined your learner or strategy to excel at the assigned task.
+In the course of creating your learning trading strategy you will probably evaluate a number of different (hyper-)parameters for your learner and your trading strategy.  Choose two of those to look at more carefully.  Conduct and report on two experiments that illustrate the methods by which you refined your learner or strategy to excel at the assigned task.
 Your descriptions should be stated clearly enough that an informed reader could reproduce the results you report.

@@ Line 12: / Line 12: @@
 * Create a regression or classification-based strategy using your Random Forest learner. Suggestions if you follow this approach: [[Classification_Trader_Hints]]. Important note, if you choose this method, you must set the leaf_size for your learner to 5 or greater.  This is to avoid degenerate overfitting in sample.
-* Create a Q-learning-based strategy using your Q-Learner. [[Q_Trader_Hints]]
+* Create a Q-learning-based strategy using your Q-Learner. Read the [[Classification_Trader_Hints]] first, because many of the ideas there are relevant for the Q trader, then see [[Q_Trader_Hints]]
 * Create a scan-based strategy using an optimizer.

@@ Line 12: / Line 12: @@
 * Create a regression or classification-based strategy using your Random Forest learner. Suggestions if you follow this approach: [[Classification_Trader_Hints]]. Important note, if you choose this method, you must set the leaf_size for your learner to 5 or greater.  This is to avoid degenerate overfitting in sample.
-* Create a Q-learning-based strategy using your Q-Learner.
+* Create a Q-learning-based strategy using your Q-Learner. [[Q_Trader_Hints]]
 * Create a scan-based strategy using an optimizer.

@@ Line 11: / Line 11: @@
 In this project you will design a learning trading agent.  You must draw on the learners you have created so far in the course.  Your choices are:
-* Create a regression or classification-based strategy using your Random Forest learner. Suggestions if you follow this approach: [[Classification_Trader_Hints]]
+* Create a regression or classification-based strategy using your Random Forest learner. Suggestions if you follow this approach: [[Classification_Trader_Hints]]. Important note, if you choose this method, you must set the leaf_size for your learner to 5 or greater.  This is to avoid degenerate overfitting in sample.
 * Create a Q-learning-based strategy using your Q-Learner.
 * Create a scan-based strategy using an optimizer.

@@ Line 11: / Line 11: @@
 In this project you will design a learning trading agent.  You must draw on the learners you have created so far in the course.  Your choices are:
-* Create a regression or classification-based strategy using your Random Forest learner. Suggestions if you follow this approach: [[Classiification_Trader_Hints]]
+* Create a regression or classification-based strategy using your Random Forest learner. Suggestions if you follow this approach: [[Classification_Trader_Hints]]
 * Create a Q-learning-based strategy using your Q-Learner.
 * Create a scan-based strategy using an optimizer.

@@ Line 3: / Line 3: @@
 * '''2017-7-11'''
 ** Project revision in progress.
 ==Overview==

← Older revision		Revision as of 01:06, 18 July 2017
Line 1:		Line 1:
−	~~==DRAFT==~~
−
−	~~This assignment is under revision. This notice will be removed once it is final.~~
−
	==Updates / FAQs==		==Updates / FAQs==

@@ Line 76: / Line 76: @@
 ==Contents of Report==
-This part of the description is still being drafted.
+Write a report describing your system.  The centerpiece of your report should be the description of how you have utilized your learner to determine trades.  Describe the steps you took to frame the trading problem as a learning problem for your learner.
 ==What to turn in==

@@ Line 134: / Line 134: @@
 ** Your learner should '''not''' select different hyper-parameters based on the '''symbol'''. Hyper-parameters include (but are not limited to) things like features, discretization size, sub-learning methods (for ensemble learners). Tuning using cross-validation or otherwise pre-processing the '''data''' is OK, things like <tt>if symbol=="UNH"</tt> are '''not OK'''. There may be a withheld test case that checks your code on a valid symbol that is not one of the four listed above.
 ** Presence of code like <tt>if symbol=="UNH"</tt> will result in a 20 point penalty.
-** When evaluating the trades generated by your learner, we '''will''' consider transaction cost (market impact and commissions).
+** When evaluating the trades generated by your learner, we '''will''' consider transaction costs (market  impact and commissions).
 '''Report: 35 points'''
-Rubric TBD
+* Is the method by which the learner is utilized to create a trading strategy described sufficiently clearly that an informed reader could reproduce the result? (up to 10 point deduction if not)
 ==Required, Allowed & Prohibited==