Spring 2019 Project 8: Strategy Learner - Revision history

Ssung40: /* Overview */

2019-04-02T02:09:12Z

Overview

Ssung40: /* Rubric */

2019-04-01T21:10:41Z

Rubric

Ssung40: /* Implement Strategy Learner */

2019-04-01T21:08:09Z

Implement Strategy Learner

Ssung40: /* Contents of Report */

2019-04-01T21:07:32Z

Contents of Report

Ssung40: /* Revisions */

2019-04-01T21:06:10Z

Revisions

Ssung40: /* Implement Strategy Learner */

2019-04-01T21:05:30Z

Implement Strategy Learner

Ssung40: /* Revisions */

2019-04-01T21:03:26Z

Revisions

Ssung40: /* Contents of Report */

2019-04-01T18:25:32Z

Contents of Report

Ssung40: /* Implement Strategy Learner */

2019-03-31T17:21:41Z

Implement Strategy Learner

Ssung40: /* Overview */

2019-03-31T17:18:53Z

Overview

@@ Line 10: / Line 10: @@
 # '''Regression''' or '''classification'''-based learner: Create a 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. For classification, you must use mode rather than mean (RTLearner, BagLearner).
 # '''Reinforcement Learner'''-based approach: 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]] For Q-learning, use the same binning cuts for in-sample and out-of-sample.
 # '''Optimization'''-based learner: Create a scan-based strategy using an optimizer.  Read the [[Classification_Trader_Hints]] first, because many of the ideas there are relevant for the Opto trader, then see [[Opto_Trader_Hints]]

@@ Line 182: / Line 182: @@
 * Does the report contain more than 6 figures and/or tables? (10 point deduction if so)
 * Does the submitted code and report reflect an understanding of the subject matter and follow the assignment directions? (up to -20 points if not)
 * Is the report especially well written (up to 2 point bonus)
 * Did the student choose to use optimization based learning, and did their learning strategy beat the manual strategy (+1 point bonus)

@@ Line 56: / Line 56: @@
 ==Implement Strategy Learner==
-For this part of the project you should develop a learner that can learn a trading policy using your learner.  You should be able to use your Q-Learner or RTLearner from the earlier project directly.  If you want to use the optimization approach, you will need to create new code or that. You will need to write code in <tt>StrategyLearner.py</tt> to "wrap" your learner appropriately to frame the trading problem for it.  Utilize the template provided in <tt>StrategyLearner.py</tt>.  <b>Be sure to add in an author method here.</b>
+For this part of the project you should develop a learner that can learn a trading policy using your learner.  You should be able to use your Q-Learner or RTLearner from the earlier project directly.  If you want to use the optimization approach, you will need to create new code or that. You will need to write code in <tt>StrategyLearner.py</tt> to "wrap" your learner appropriately to frame the trading problem for it.  Utilize the template provided in <tt>StrategyLearner.py</tt>.  Be sure to add in an author method.
 Your StrategyLearner should implement the following API:

@@ Line 85: / Line 85: @@
 * Describe the steps you took to frame the trading problem as a learning problem for your learner. What are your indicators? (They should be the same ones used for Manual Strategy assignment) Describe how you discretized (standardized) or otherwise adjusted your data. If not, tell us why not.
-*Experiment 1: Using exactly the same indicators that you used in manual_strategy (trade JPM), compare your manual strategy with your learning strategy in sample. You can use the same impact (.005) as was used for Project 6 or use 0 for both.
+*Experiment 1: Using exactly the same indicators that you used in manual_strategy (trade JPM), compare your manual strategy with your learning strategy in sample. You can use the same impact (.005) as was used for Project 6 or use 0 for both. Be sure to add in an author method.
 ** Describe your experiment in detail: Assumptions, parameter values and so on.
 ** Describe the outcome of your experiment.
 ** Would you expect this relative result every time with in-sample data?  Explain why or why not.
-* Experiment 2: Provide a hypothesis regarding how changing the value of <tt>impact</tt> should affect in sample trading behavior and results (provide at least two metrics). Conduct an experiment with JPM on the in sample period to test that hypothesis.  Provide charts, graphs or tables that illustrate the results of your experiment. The code that implements this experiment and generates the relevant charts and data should be submitted as <tt>experiment2.py</tt>
+* Experiment 2: Provide a hypothesis regarding how changing the value of <tt>impact</tt> should affect in sample trading behavior and results (provide at least two metrics). Conduct an experiment with JPM on the in sample period to test that hypothesis.  Provide charts, graphs or tables that illustrate the results of your experiment. The code that implements this experiment and generates the relevant charts and data should be submitted as <tt>experiment2.py</tt>. Be sure to add in an author method.
 Your descriptions should be stated clearly enough that an informed reader could reproduce the results without referencing your code.

@@ Line 3: / Line 3: @@
 This assignment is subject to change up until 3 weeks prior to the due date. We do not anticipate changes; any changes will be logged in this section.
 * Edits and cleanup. (Overview, Template, Contents, Rubric, etc)
-* Requirement for author method in all submitted files.
+* Requirement for author method in all submitted code files.
 ==Overview==

@@ Line 8: / Line 8: @@
 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:
-# '''Regression''' or '''classification'''-based learner: Create a 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. For classification, you must use mode rather than mean.
+# '''Regression''' or '''classification'''-based learner: Create a 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. For classification, you must use mode rather than mean (RTLearner, BagLearner).
 # '''Reinforcement Learner'''-based approach: 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]] For Q-learning, use the same binning cuts for in-sample and out-of-sample.