MC3-Project-3 - Revision history

Tucker: /* Updates / FAQs */

2017-05-19T23:04:10Z

Updates / FAQs

Tucker: /* Updates / FAQs */

2017-04-10T15:07:44Z

Updates / FAQs

Tucker: /* Contents of Report */

2017-04-05T21:11:36Z

Contents of Report

Tucker: /* Updates / FAQs */

2017-04-02T14:50:20Z

Updates / FAQs

Tucker: /* Part 2: Best Possible Strategy (5%) */

2017-04-02T14:49:12Z

Part 2: Best Possible Strategy (5%)

Vkhurana9: /* Updates / FAQs */

2017-03-31T14:54:00Z

Updates / FAQs

Tucker: /* Hints */

2017-03-30T14:49:17Z

Hints

Tucker: /* Rubric */

2017-03-29T21:57:55Z

Rubric

Tucker: /* Rubric */

2017-03-29T21:57:30Z

Rubric

Tucker: /* Rubric */

2017-03-29T21:49:49Z

Rubric

← Older revision		Revision as of 23:04, 19 May 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 19: / Line 19: @@
 * Q: I want to read some other values from the data besides just adjusted close, how can I do that? A: Please modify an old version of util.py to do that, include that new util.py with your submission.
-* Q: Are we required to trade in only 200 share blocks? (and have no more than 200 shares long or short at a time as in some of the previous assignments)  A: Yes.  This will enable comparison between results more easily.
+* Q: Are we required to trade in only 200 share blocks? (and have no more than 200 shares long or short at a time as in some of the previous assignments)  A: (update).  You can trade up to 400 shares at a time as long as you maintain the requirement of 200, 0 or -200 shares.  This will enable comparison between results more easily.
 * Q: Are we limited to leverage of 2.0 on the portfolio?  A: There is no limit on leverage.

@@ Line 217: / Line 217: @@
 ==Contents of Report==
-* Your report should be no more than 3000 words.  Your report should contain no more than 12 charts.  Penalties will apply if you violate these constraints.
+* Your report should be no more than 3000 words.  Your report should contain no more than 14 charts.  Penalties will apply if you violate these constraints.
 * Include charts and text as identified in the sections above.

← Older revision		Revision as of 14:50, 2 April 2017
Line 1:		Line 1:
	==Updates / FAQs==		==Updates / FAQs==
		+
		+	*'''2017-04-02'''
		+	** Clarified instructions regarding "best possible" to use your own market simulator with adjusted closing prices.

	*'''2017-03-16'''		*'''2017-03-16'''

@@ Line 58: / Line 58: @@
 ==Part 2: Best Possible Strategy (5%)==
-Assume that you can see the future, but that you are constrained by the portfolio size and order limits as specified above.  Create a set of trades that represents the best a strategy could possibly do during the in sample period. The holding time requirements described in the next sections do not apply to this exercise.  The reason we're having you do this is so that you will have an idea of an upper bound on performance.  Provide a chart that reports:
+Assume that you can see the future, but that you are constrained by the portfolio size and order limits as specified above.  Create a set of trades that represents the best a strategy could possibly do during the in sample period. The holding time requirements described in the next sections do not apply to this exercise.  The reason we're having you do this is so that you will have an idea of an upper bound on performance.
 * Benchmark (see definition above) normalized to 1.0 at the start: Black line

@@ Line 10: / Line 10: @@
 * Q: In a previous project there was a constraint of holding a single position until exit. Does that apply to this project?  Yes, hold one position til exit.
-* Q: Is that 10 calendar days, or 10 trading days (i.e., days when SPY was traded)? A: Always use trading days.
+* Q: Is that 21 calendar days, or 21 trading days (i.e., days when SPY was traded)? A: Always use trading days.
 * Q: Are there constraints for Python modules allowed for this project? Can we experiment with modules for optimization or technical analysis and cite or are we expected to write everything from scratch for this project as well?  A: The constraints are the same as for the first learning project. You've already written the learners you need.
@@ Line 16: / Line 16: @@
 * Q: I want to read some other values from the data besides just adjusted close, how can I do that? A: Please modify an old version of util.py to do that, include that new util.py with your submission.
-* Q: Are we required to trade in only 500 share blocks? (and have no more than 500 shares long or short at a time as in some of the previous assignments)  A: Yes.  This will enable comparison between results more easily.
+* Q: Are we required to trade in only 200 share blocks? (and have no more than 200 shares long or short at a time as in some of the previous assignments)  A: Yes.  This will enable comparison between results more easily.
 * Q: Are we limited to leverage of 2.0 on the portfolio?  A: There is no limit on leverage.
-* Q: Are we only allowed one position at a time?  A: You can be in one of three states: -500 shares, +500 shares, 0 shares.
+* Q: Are we only allowed one position at a time?  A: You can be in one of three states: -200 shares, +200 shares, 0 shares.
 ==Overview==

@@ Line 194: / Line 194: @@
 Your code should classify based on 21 day change in price.  You need to build a new Y that reflects the 21 day change and aligns with the current date.  Here's pseudo code for the calculation of Y
-  ret = (price[t+10]/price[t]) - 1.0
+  ret = (price[t+21]/price[t]) - 1.0
   if ret > YBUY:
       Y[t] = +1 # LONG

@@ Line 269: / Line 269: @@
 * Is the Y data in the train and query plots similar (-5% if not)
-Comparative analysis (up to 20% deductions):
+Comparative analysis (up to 10% deductions):
 * Is the appropriate chart provided (-5% for each missing element, up to a maximum of -10%)
 * Is there a table that reports in-sample and out-of-sample data for the baseline (just the stock), rule-based, and ML-based strategies? (-5% for each missing element)

@@ Line 263: / Line 263: @@
 * Does the submitted code <tt>ML_based.py</tt> properly reflect the strategy provided in the report? (-30% if not)
 * Does the ML trading system provide 1.5x higher cumulative return or than the benchmark over the in-sample time period? (-5% if not)
 Comparative analysis (up to 20% deductions):

@@ Line 244: / Line 244: @@
 * Is the trading strategy described with clarity and in sufficient detail that someone else could reproduce it? (-10%)
 * Does the provided chart include:
-** Historic value of IBM normalized to 1.0 with black line (-5% if not)
+** Historic value of benchmark normalized to 1.0 with black line (-5% if not)
 ** Historic value of portfolio normalized to 1.0 with blue line (-10% if not)
 ** Are the appropriate date ranges covered? (-5% if not)