Since my last post on the currency strength indicator I have been conducting a series of basic randomisation tests to see if the indicator has better than random predictive ability. The first test was a random permutation test, as described in Aronson's Evidence Based Technical Analysis book,

Over the last few weeks I have been looking into creating a currency strength indicator as input to a Nonlinear autoregressive exogenous model. This has involved a fair bit of online research and I have to say that compared to other technical analysis indicators there seems to be a paucity of pages

In my last post I said I was going to look at data wrangling my data, and this post outlines what I have done since then. My problem was that I have numerous csv files containing historical data with different date formats and frequency, e.g. tick level and hourly and daily OHLC, and in the past I

It has been over three months since my last post, due to working away from home for some of the summer, a summer holiday and moving home. However, during this time I have continued with my online reading and some new thinking about my conditional restricted boltzmann machine based trading system has

I have spent the last few weeks trying to get my recursive sine wave formula for period calculations to work, but try as I might I can only get it to do so under ideal theoretical conditions. Once any significant noise, trend or combination thereof is introduced the calculations explode and give

It has been a while since my last post and in the intervening time I have been busy working on the code of my previous few posts. During the course of this I have noticed that there are some further improvements to be made in terms of robustness etc. inspired by this Master's thesis, Improved

This code box contains updated code from my previous post. The main change is the inclusion of bias units for the directed auto-regressive weights and the visible to hidden weights. In addition there is code showing how data is pre-processed into batches/targets for the pre-training and code showing

Since my last post I have been doing a fair bit of online research and fortunately I have discovered the following papers, which mesh nicely with what I am trying to do with Conditional Restricted Boltzmann Machines to model time series:- Deep Learning Architecture for Univariate Time Series

Over the last few weeks I have been looking at using Runge-Kutta methods for the creation of features, but I have decided to give up on this for now simply because I think I have found a better way to accomplish what I want. I was alerted to this possible approach by this post over at

Following on from my last post I thought I would, as a first step, code up a "straightforward" Runge-Kutta function and show how to deal with the fact that there is no "magic mathematical formula" to calculate the slopes that are an integral part of Runge-Kutta. My approach is to

As stated in my previous post I have been focusing on getting some meaningful features as possible inputs to my machine learning based trading system, and one of the possible ideas that has caught my attention is using Runge-Kutta methods to project ( otherwise known as "guessing" ) future

I've recently subscribed to this forexfactory thread, which is about using machine learning to develop trading systems, and the subject of data mining/data dredging has come up. This post is a short description of how mining/dredging can be accounted for, but readers should be aware that the

Following on from the successful C++ .oct coding of the Gaussian and Binary units, I thought I would conduct a simple visual test of the conditional restricted boltzmann machine, both as a test of the algorithm itself and of my coding of the .oct functions. For this I selected a

Over the last few weeks I have been working on optimising the conditional restricted boltzmann machine code, with a view to speeding it up via a C++ .oct file, and in the code box below is this .oct code for the gaussian_crbm.m code in my previous post. This gaussian_crbm.m function, plus the

I have recently been looking at using a Conditional Restricted Boltzmann Machine, and in particular Graham Taylor's thesis paper, Composable Distributed-State Models for High-Dimensional Time Series and the associated code available from here. My adaptation of this is very much a work in

Following on from my last post, here is an Octave .oct file implementation of the one dimensional Particle swarm optimisation routine, with one slight twist: instead of using a for loop I've implemented it within a while loop with a stopping condition that the algorithm should cease once there

Having decided that I'm going to use my mfe_mae indicator as a target for my neural net, over the last couple of months I've been doing some research on what would make good features for this target. In the course of this I've also decided that Particle swarm optimization would be a