Spring 2020 Project 8: Strategy Evaluation - Revision history

Jfox44: /* Revisions */

2020-04-02T01:54:47Z

Revisions

2020-04-02T01:54:03Z

Template

2020-03-30T01:53:22Z

Revisions

2020-03-30T01:52:40Z

Implement Strategy Learner

2020-03-30T01:48:08Z

Implement Strategy Learner

2020-03-26T13:36:20Z

Revisions

2020-03-26T13:35:27Z

Overview

2020-03-22T23:47:06Z

2020-01-02T01:13:33Z

2020-01-02T01:07:00Z

Created page with "Under Construction"

New page

Under Construction

@@ Line 9: / Line 9: @@
 /26/2020 Removed parameter optimization limitations from Overview/StrategyLearner
 /29/2020 Added verbiage that lookback window tuning is optional and not required.
 ==Overview==

@@ Line 40: / Line 40: @@
 * Download and install the files from this zip file [[File:20Spring_strategy_evaluation.zip]]
 * <tt>ManualStrategy.py</tt> Code implementing a ManualStrategy object (your <b>Manual Strategy</b>) in the <tt> strategy_evaluation/</tt> directory.  It should implement testPolicy() which returns a trades data frame (see below). The main part of this code should call marketsimcode as necessary to generate the plots used in the report. NOTE: You will have to create this file yourself.
-* Place your existing Q-Learner or RTLearner (Okay to include DTLearner as well if inheritance is involved) or OptimizationLearner into the <tt>strategy_evaluation/</tt> directory.
+* Place your existing Q-Learner or RTLearner and BagLearner (Okay to include DTLearner as well if inheritance is involved) or OptimizationLearner into the <tt>strategy_evaluation/</tt> directory.
 * Place your existing indicators.py into the <tt>strategy_evaluation/</tt> directory (NOTE: You can make changes to the indicators to properly work with both <b>Manual Strategy</b> and <b>Strategy Learner</b> but both strategies must use the same indicator code).
 * Place your existing marketsimcode.py into the <tt>strategy_evaluation/</tt> directory (optional: if needed).

← Older revision		Revision as of 01:53, 30 March 2020
Line 8:		Line 8:

	3/26/2020 Removed parameter optimization limitations from Overview/StrategyLearner		3/26/2020 Removed parameter optimization limitations from Overview/StrategyLearner
		+	3/29/2020 Added verbiage that lookback window tuning is optional and not required.

	==Overview==		==Overview==

@@ Line 90: / Line 90: @@
 For this part of the project you should develop a learner that can learn a trading policy using your learner and the same indicators used in ManualStrategy (NOTE: You can make changes to the indicators to properly work with both <b>Manual Strategy</b> and <b>Strategy Learner</b> but both strategies must use the same indicator code).  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 for 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>.
-Your Strategy Learner should find the optimal parameters for each indicator. Example: for SMA the learner should find the optimal lookback window to use.
+Your Strategy Learner should find the optimal parameters **that you choose to optimize** for each indicator. Example: for SMA the learner <tt>could</tt> find the optimal lookback window to use.
 Your StrategyLearner should implement the following API:

@@ Line 90: / Line 90: @@
 For this part of the project you should develop a learner that can learn a trading policy using your learner and the same indicators used in ManualStrategy (NOTE: You can make changes to the indicators to properly work with both <b>Manual Strategy</b> and <b>Strategy Learner</b> but both strategies must use the same indicator code).  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 for 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>.
-Your Strategy Learner should find the optimal parameters for each indicator. Example: for SMA the learner should find the optimal loopback window to use.
+Your Strategy Learner should find the optimal parameters for each indicator. Example: for SMA the learner should find the optimal lookback window to use.
 Your StrategyLearner should implement the following API:

← Older revision		Revision as of 13:36, 26 March 2020
Line 6:		Line 6:

	This assignment is subject to change up until 3 weeks prior to the due date. We do not anticipate any major changes; any changes will be logged in this section.		This assignment is subject to change up until 3 weeks prior to the due date. We do not anticipate any major changes; any changes will be logged in this section.
		+
		+	3/26/2020 Removed parameter optimization limitations from Overview/StrategyLearner

	==Overview==		==Overview==

@@ Line 21: / Line 21: @@
 *** In the training phase (e.g., addEvidence()) your learner will be provided with a stock symbol and a time period.  It should use this data to learn a strategy. For instance, for a regression-based learner it will use this data to make predictions about future price changes.
 *** In the testing phase (e.g., testPolicy()) your learner will be provided a symbol and a date range. All learning should be turned OFF during this phase.
-*** You should use exactly the same indicators as you use in the <b>Manual Strategy</b> so we can compare your results. You may optimize your indicators for time (vectorization), but there should be no changes to lookback windows or any other pertinent parameters.
+*** You should use exactly the same indicators as you use in the <b>Manual Strategy</b> so we can compare your results. You may optimize your indicators for time (vectorization).
 **If the date range is the same as used for the training, it is an in-sample test. Otherwise it is an out-of-sample test.  Your learner should return a trades dataframe like it did in the last project.  Here are some important requirements: Your testPolicy() method should be much faster than your addEvidence() method. The timeout requirements (see rubric) will be set accordingly.  Multiple calls to your testPolicy() method should return exactly the same result.

← Older revision		Revision as of 01:13, 2 January 2020
Line 1:		Line 1:
−	~~Under Construction~~	+	==Revisions==
		+
		+	==Overview==
		+
		+	== Template==
		+
		+	==Tasks==
		+
		+	==What to turn in==
		+
		+	==Rubric==
		+
		+	===Report===
		+
		+	===Code===
		+
		+	==Required, Allowed & Prohibited==