Difference between revisions of "MC3-Project-2"
| Line 9: | Line 9: | ||
In this project you will transform your regression learner into a stock trading strategy. Overall, you should follow these steps: | In this project you will transform your regression learner into a stock trading strategy. Overall, you should follow these steps: | ||
| − | * Train a regression learner (KNN or LinReg, or other of your choice with or without bagging) on data from 2008 to 2009. | + | * Train a regression learner (KNN or LinReg, or other of your choice with or without bagging) on data from 2008 to 2009. This is your in sample training data. |
** For your X values: Identify and implement at least 3 technical features that you believe may be predictive of future return. You should implement them so they output values typically ranging from -1.0 to 1.0. This will help avoid the situation where one feature overwhelms the results. See a few formulae below. | ** For your X values: Identify and implement at least 3 technical features that you believe may be predictive of future return. You should implement them so they output values typically ranging from -1.0 to 1.0. This will help avoid the situation where one feature overwhelms the results. See a few formulae below. | ||
** For your Y values: Don't use price, use 5 day return. | ** For your Y values: Don't use price, use 5 day return. | ||
| Line 16: | Line 16: | ||
* Create a plot that illustrates entry and exits as vertical lines on a price chart for the in sample period 2008-2009. Show long entries as green lines, short entries as red lines and exits as black lines. You may find it convenient to zoom in on a particular time period so this is evident. | * Create a plot that illustrates entry and exits as vertical lines on a price chart for the in sample period 2008-2009. Show long entries as green lines, short entries as red lines and exits as black lines. You may find it convenient to zoom in on a particular time period so this is evident. | ||
* Now use your code to generate orders and run those orders through your market simulator. Create a chart of this backtest. It should do VERY well for the in sample period 2008-2009. | * Now use your code to generate orders and run those orders through your market simulator. Create a chart of this backtest. It should do VERY well for the in sample period 2008-2009. | ||
| − | * Now | + | * Freeze your model based on the 2008-2009 data. Now test it for the year 2010 -- Plot that illustrates entry & exits, generate trades, run through simulator, chart the backtest. |
| + | |||
| + | Perform the above steps first using the data ML4T-399.csv, once you've validated success (it should work well), repeat using IBM data over the same dates. Remember 2008-2009 is training, 2010 is testing. You should have one set of charts for each symbol. | ||
==Template and Data== | ==Template and Data== | ||
Revision as of 17:52, 20 November 2015
Contents
Draft
"Draft" will be removed when the assignment is final.
Updates / FAQs
Overview
In this project you will transform your regression learner into a stock trading strategy. Overall, you should follow these steps:
- Train a regression learner (KNN or LinReg, or other of your choice with or without bagging) on data from 2008 to 2009. This is your in sample training data.
- For your X values: Identify and implement at least 3 technical features that you believe may be predictive of future return. You should implement them so they output values typically ranging from -1.0 to 1.0. This will help avoid the situation where one feature overwhelms the results. See a few formulae below.
- For your Y values: Don't use price, use 5 day return.
- Create a plot that illustrates your Y values in one color and price in another color, we should be able to see that your Y values are shifted back 5 days. You may find it convenient to zoom in on a particular time period so this is evident.
- Create a trading policy based on what your learner predicts for future return. As an example you might choose to buy when the forecaster predicts the price will go up more than 1%, then hold for 5 days.
- Create a plot that illustrates entry and exits as vertical lines on a price chart for the in sample period 2008-2009. Show long entries as green lines, short entries as red lines and exits as black lines. You may find it convenient to zoom in on a particular time period so this is evident.
- Now use your code to generate orders and run those orders through your market simulator. Create a chart of this backtest. It should do VERY well for the in sample period 2008-2009.
- Freeze your model based on the 2008-2009 data. Now test it for the year 2010 -- Plot that illustrates entry & exits, generate trades, run through simulator, chart the backtest.
Perform the above steps first using the data ML4T-399.csv, once you've validated success (it should work well), repeat using IBM data over the same dates. Remember 2008-2009 is training, 2010 is testing. You should have one set of charts for each symbol.
Template and Data
You will use data in the ML4T/Data directory. In particular files named ML4T-XXX.csv, where XXX are digits.
Part 1: Build TrainY
Use ML4T-399.csv
Your code should predict 5 day change in price. You need to build a new Y that reflects the 5 day change and aligns with the current date.
Create a plot that shows current price and overlays the 5 day change, and overlays one on the other. The result should appear to be just a shifted version of the price.
Part 3: Develop Technical Indicators
Select and implement at least 3 technical indicators that you will use to predict prices.
Part 4: Train and Show Results
Train your system on 2008-2009. Create a chart that shows your predicted 5 day return versus actual.
Part 5: Create a Trading Strategy
Use your forecaster to generate a trading strategy. Create a chart that shows entry and exit points.
Generate trades, show backtest. Show results for in sample (2008-2009) and out of sample 2010-2011
Apply this now to real data, IBM, over the same period.
