The term statistical arbitrage (stat-arb) encompasses a wide variety of investment strategies that typically aim to exploit a statistical equilibrium relationship between two or more securities. The general principal is that any divergence from the equilibrium is a temporary effect and that bets

This post explores applying NEAT to trading the S&P. The learned strategy significantly out performs buying and holding both in and out of sample. Features: A key part of any machine learning problem is defining the features and ensuring that they’re normalised in some fashion. The features

A simple tutorial demonstrating how to train a neural network to square root numbers using a genetic algorithm that searches through the topological structure space. The algorithm is called NEAT (Neuro Evolution of Augmenting Topologies) available in the RNeat package (not yet on CRAN). The training

This part of the tutorial on using NEAT algorithm explains how genomes are crossed over in a meaningful way maintaining their topological information and how speciation (group genomes into species) can be used to protect weak genomes with new topological information from prematurely being eradicated

This four part series will explore the NeuroEvolution of Augmenting Topologies (NEAT) algorithm. Parts one and two will briefly out-line the algorithm and discuss the benefits, part three will apply it to the pole balancing problem and finally part 4 will apply it to market data. This algorithm

Part 3 of this series demonstrated how to train a HMM on a toy model, this post will focus on how to actually go about modelling real life data. A trend following strategy will be developed for trading the S&P 500. In most machine learning classification problems you need a set of training data