Consider now that we change the model to a still simple yet more powerful classifier (a K-Nearest Neighbor approach) using the same input/target structure as above (two past days to predict next day's directionality). However we now have a stoploss ...

Machine Learning with algoTraderJo

The above generates the more interesting how questions: How do we know that an input has predictive power? How do we distinguish profitable results from the results our machine learning model can give due to random chance? (how to measure data ...

Machine Learning with algoTraderJo

However if I understand correctly what you are doing with this seems to be to get an estimate of the current trending state of the market, this might not be that useful since you're interested in the future and not in the state that has developed up ...

Kalman filter and currencies strength

It's interesting to think about what might be wrong in the above example: Did we choose the wrong model? (the relationship is too complex for our model to make out) Did we choose the wrong inputs? (the inputs have no relationship with the targets, ...

Machine Learning with algoTraderJo

Let us get down to business now. A real practical example using machine learning. Let's suppose we want to build a very simple model using a very simple set of inputs/targets. For this experiment these are the answers to the questions: What to ...

Machine Learning with algoTraderJo

I want to start by saying some basic things. I am sorry if the structure of my posts leaves a lot to be desired, I don't have any forum posting experience but hope to get some with time. In machine learning what we want to do is simply to generate a ...

Machine Learning with algoTraderJo

Glad to hear some of you have already subscribed! I hope to make things interesting for you

Machine Learning with algoTraderJo

The key aspect here is that a trader must be able to predict market directionality across a given time horizon after an entry happens. The quality of an entry can be measured by the maximum favorable excursion (MFE) and maximum adverse excursion ...

Does timing of entry really matter, or just direction?

I wonder if you have ever thought about using your KF measurements as part of an input for a machine learning system to get trading signals? Some of the systems I use take advantage of similar measurements of currency strength/weakness and have ...

Kalman filter and currencies strength

When you are using a single system it is not possible for you to obtain a money management technique that is statistically any better than the general percentage based management. You can get fooled very easily by simulations (or historical results ...

Money management - What is the secret?

I have been a silent ForexFactory reader for a while, this finally prompted me to post. I do believe that using a method where you constantly gauge trade continuation probabilities is the best choice. I use machine learning to evaluate the ...

Some silly ways of looking at P/L