Search results

The reason is the normal distribution of returns. Let's suppose you want to bet only on the long side. For every 10% up move, there is going to be 5 2% down moves or 3.333 3% down moves on average in the long run, so you're still 50/50. Your betting scheme is not going change the expectation of...

Hi all, Let's assume that a certain aspect of the price movement is a random distribution process. We plot two points on the distribution curve that are not too far apart, plug in two sensors at the points and take readings. If the points are not too far apart, the curve is nearly linear, so...

I agree, backtesting is just another way of curve fitting - selecting trading rules that perform well on a particular data segment. Seven years? LOL. The model ( with the current frequency (that can be adjusted)) would generate some 100k signals or more. That would be very statistically...

Here are some more charts from Wednesday's session. This time from the first few hours of trading. When the Primary Momentum (based on the tradable) moves up or down and the Secondary Momentum (the model) does not confirm the move, price will adjust to liquidate the difference. As I mentioned...

It is not yet a complete trading system that can be backtested. It is a method of indicating trading opportunities - an edge.

Apparently other market participants detect the same inefficiencies using their own methods and enter orders to take advantage of them.

I am pretty sure it will, for two reasons. One, the inefficiencies will continue to exist. Two, the model is not a result of data mining, parameter optimization, neural network training, etc. - it will not deteriorate with time.

I decided to show the inefficiencies in the form of divergences between two oscillators (of the same order, frequency, normalization, etc.) because it possibly is the easiest way to see them. This not a complete trading system yet. This method generates so many signals, that only the "best"...

How do your generated reversal signals compare to price/momentum divergence signals? In the case of price/momentum divergence, you compare a function with its first or second derivative, i.e. the time series with its corresponding speed and acceleration. They show devergence because you...

Instead of searching for an edge through data mining, how about designing an edge? I came up with a theory how the market "should" move and coded two oscillators that show how the market is moving and how it "should" move. The Primary Momentum is based on actual price movement and the...