Timeline for Normalization of financial price to use as input in a neural network
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 25, 2020 at 18:49 | vote | accept | unter_983 | ||
| Aug 25, 2020 at 18:47 | comment | added | kurtosis | Depending on how you structure your other inputs, you could specify the max and min as prices (probably troublesome) or as log-returns versus the opening price or last price (more useful when comparing to volatility estimates). | |
| Aug 25, 2020 at 18:44 | comment | added | unter_983 | I'm working on a reinforcement learning model for trading with a DQN, and I would like to include even maximum/minimum price as inputs | |
| Aug 25, 2020 at 18:14 | comment | added | kurtosis | You could maybe use something different, but that would depend on what you are trying to estimate since there are only a few instances where using something else is justifiable. | |
| Aug 25, 2020 at 6:11 | comment | added | unter_983 | Yes, I know in fact I already use log-returns as an input variable. But daily prices offer different values as the maximum price or the minimum price: what to do to insert even those variables in a neural net? Do you mean I have to use log-returns for each type of price (i.e. log-returns of the time series of max prices ...)? | |
| Aug 25, 2020 at 1:07 | history | answered | kurtosis | CC BY-SA 4.0 |