Machine Learning

Machine Learning / NeuroNetworks 

It is time than Machine Learning / AI / NeuroNetworks have stabilized the common framework to speak with "standardized" language and there are enough computer power available via GPUs and clouds to utilize those methods fast enough. (so I'm back ... started AI long long time ago but it vanished for decades..)
So it is time to develop something to NinjaTrader side as well.

Most of the current research and open development happen at Linux environments via Python (numpy, scipy, sklearn, ...) or R. Unfortunately Googles TensorFlow is not available directly to Windows yet but lets see. Update: It is available now!

Some references  and courses even at trading (there are much more general ones so get familiar):
Machine Learning for Trading

Support functions to Machine Learning will be added time to time (as those might interest someone) although similar techniques has already used at some indicators like inside PVExtraRegression and so on.

MLTimeState (Intraday = Session Time)

This is the first of the series Machine Leaning Support Functions  (Starting with letters ML)
but this can be utilized at normal trading as well.  Use this to normalize the time (1 - 0] and or use time as a STATE (map this to matrix via Machine Learning to find out the best times)  or  think this as a time left to trade and some sort of probabilistic model time.

Other:

Basically this is a linear line from 1 (=session begin) to 0 (=session end)  based to session time, if you need exponential or logarithmic model, that can be done as well (this current model / indicator does not use any parameter to keep the function clear).
Hint: use  (int) Time[0].DayOfWeek as one own indicator to the machine learning functions as well as every day has it own common charasterics and there are reasons for that.

Download: NT7 NT8 

Purchase: Part of MLTools

License: MLTools

MLIndicatorI: Index: 134

Picture:

Be free to try at your side as well (don't get confused with PVAdaptiveVTR Bars here in the picture, PVAMA is my own adaptive MA).

MLHighLowTimes

Another support function but this is a Multi Time Frame (internal accuracy 1 min) to get a normalized time  Day High and Day Low Time values from the session (checked inside bar), FYI it's vice verse so 0 is a session start and 1 session end to understanding time better if you look numerically (so later time has a bigger value).In principle it shouldn't be any difference when as you train the NN weights but better to remember.


Example to see how it behaves:

Typical usage at day 1 bars or 1440 min...:

Example Usage: use  the value at NeuroNetwork for next day after session end (time to calculate and train the network, something what it can able to support and detect and classify like short squeezes, ...).


FYI, this last AILowTimes has been used at those first initial very promising tests.

Risk Disclosure: Futures and forex trading contains substantial risk and is not for every investor. An investor could  potentially lose all or more than the initial investment. Risk capital is money that can be lost without jeopardizing ones’ financial security or life style. Only risk capital should be used for trading and only those with sufficient risk capital should consider trading. Past performance is not necessarily indicative of future results. 

Hypothetical Performance Disclosure: Hypothetical performance results have many inherent limitations, some of which are described below. no representation is being made that any account will or is likely to achieve profits or losses similar to those shown; in fact, there are frequently sharp differences between hypothetical performance results and the actual results subsequently achieved by any particular trading program. One of the limitations of hypothetical performance results is that they are generally prepared with the benefit of hindsight. In addition, hypothetical trading does not involve financial risk, and no hypothetical trading record can completely account for the impact of financial risk of actual trading. for example, the ability to withstand losses or to adhere to a particular trading program in spite of trading losses are material points which can also adversely affect actual trading results. There are numerous other factors related to the markets in general or to the implementation of any specific trading program which cannot be fully accounted for in the preparation of hypothetical performance results and all which can adversely affect trading results.
Terms of Usage