Latest update
- The 70 weeks in Daniel 9
- What is a piezo pickup and how does it differ to a common pickup?
- Why do we have same chord but different name?
- Seagull S6 acoustic guitar feels very hard to play
- Add apps using custom master page
- Questions about “Peaceful Parent, Happy Kids”
- My parents never believe what I have to say or believe in me (trust issues around amount of effort being put into schoolwork)
- Car alternator or battery problem?
- Gas pedal floored yet the car can't reach maximum speed
- drush8 for D7&D8
- Process service call after sending response
- Forum Advanced solution on Drupal 8
- Impact on hypertrophy: 2 sets vs. 3 sets for every different exercise
- Reduce the complexity of following code - is it possible?
- Throttle submissions to ExecutorService
- Is movie Beyond Skyline based on the book A Plague of Demons?
- Book where a young man gathers memories from formaldehyde-preserved animals and minds
- Is it possible for a wooden ship to carry a ballista inside the hull that fires from the prow
- What was that movie with the man with the robot arm?
- How to query more than one criterion on PostgreSQL
Appropriate way to normalize Bollinger Bands?
2018-03-16 00:29:06
I am playing around with using neural nets to make predictions on market trends. I am currently feeding in a portfolio of historical data of many stocks, and am now implementing several technical indicators into my data set.
As of now, I am just attempting to predict up or down trends, and so I have made all of my data stationary - for example rather than feeding in raw sequences of closing prices, I instead feed in the normalized percentage change of the closing price from one time point to the next.
I am looking to incorporate Bollinger Bands into my data to see if they have any impact, but I am struggling to figure out how to apply a similar detrending technique. One method I have thought of is to calculate the difference between the upper and middle band, and between the middle and lower band at each time point, and then normalise both of these values.
Any thoughts on this? Any other recommendations?
You may notice that the difference between the middle bands
-
You may notice that the difference between the middle bands and upper and lower bands is simply a constant of realized standard deviation of price. If you want to feed a prediction algorithm some standardized data which is comparable for all securities, I would suggest indicators which operate on logarithmic price changes.
2018-03-16 02:42:51