Image Image Image Image Image Image Image Image Image Image

Turing Finance | January 20, 2017

Scroll to top


Fitness Landscape Analysis for Computational Finance

June 29, 2015 | | 11 Comments

Some of the most interesting new research coming out of the Computational Intelligence Research Group (CIRG), which is applicable to numerous computational finance and machine learning optimization problems, is the development of fitness landscape analysis techniques. Fitness landscape analysis aims to characterize high dimensional ... Read More

A Recipe for the 2008 Financial Crisis

May 5, 2015 | | 13 Comments

In 2008 when the market crashed I was 16-years old and visiting London for the very first time. At that age I was already obsessed with the markets. Feeling confident that I could understand the crash after having read the classic investment books such ... Read More

Random walks down Wall Street, Stochastic Processes in Python

April 7, 2015 | | 29 Comments

James Bond is not a quant, but many famous quantitative fund managers enjoy playing poker in their spare time. Stochastic processes can be used to model the odds of such games. This article discusses some of the popular ... Read More

Monte Carlo K-Means Clustering of Countries

February 9, 2015 | | 20 Comments

In the first part of this three-part series, What Drives Real GDP Growth?, I identified four themes which drive real GDP growth. These themes are based on 19 socioeconomic indicators whose average Spearman and Pearson correlations to real GDP growth were statistically ... Read More

What Drives Real GDP Growth?

January 15, 2015 | | 6 Comments

Econometrics is the application of statistical and computational techniques to the study of economic data. It differs from classical economics in that it is based on empirical findings rather than theories. One benefit of this approach is that ... Read More

Dimensionality Reduction Techniques

October 27, 2014 | | 14 Comments

The curse of dimensionality is the phenomena whereby an increase in the dimensionality of a data set results in exponentially more data being required to produce a representative sample of that data set. To combat the curse of dimensionality, numerous linear and non-linear dimensionality reduction ... Read More

All Models are Wrong, 7 Sources of Model Risk

September 6, 2014 | | 9 Comments

The 2008 financial crisis revealed to the world (in spectacular fashion) the fragility of financial models. Since the financial crisis two words have come up time and time again: model risk. This article defines model risk and discusses some of the contributors ... Read More

Computational Finance at IEEE WCCI 2014

July 27, 2014 | | 3 Comments

I recently had the awesome opportunity to present my honours research at this years IEEE World Congress for Computational Intelligence conference (IEEE-WCCI) in Beijing. My trip was sponsored by the University of Pretoria's Computational Intelligence Research Group (CIRG) so ... Read More

Regression analysis using Python

June 7, 2014 | | 16 Comments

This tutorial covers regression analysis using the Python StatsModels package with Quandl integration. For motivational purposes, here is what we are working towards: a regression analysis program which receives multiple data-set names from, automatically downloads the data, analyses it, and plots the results ... Read More

10 misconceptions about Neural Networks

May 8, 2014 | | 51 Comments

Neural networks are one of the most popular and powerful classes of machine learning algorithms. In quantitative finance neural networks are often used for time-series forecasting, constructing proprietary indicators, algorithmic trading, securities classification and credit risk modelling. They ... Read More

Simulated Annealing for Portfolio Optimization

March 15, 2014 | | One Comment

This article applies the Simulated Annealing (SA) algorithm to the portfolio optimization problem. Simulated Annealing (SA) is a generic probabilistic and meta-heuristic search algorithm which can be used to find acceptable solutions to optimization problems characterized by a large ... Read More

Computational Decision Making Methods

February 13, 2014 | | One Comment

Artificial intelligence is broadly defined as the ability of an agent or a model to make either optimal or satisficing decisions. Decision-making in this context is a process which culminates in the selection of a particular course of ... Read More

Graph Theory for Systemic Risk Models

January 29, 2014 | | 5 Comments

The markets around the world are highly connected. The risk that the entire financial system crashes as a result of the failure of one or more entities is called systemic risk. The 2008 Financial Crisis demonstrated first hand ... Read More

Agent-based Computational Economic Models

January 13, 2014 | | 3 Comments

Economists subscribe to many often contradictory schools of thought. This results in businesses and governments adopting economic policies whose consequences are neither agreed upon nor understood. Furthermore, because the economy is actually a complex adaptive system most traditional economic ... Read More

Portfolio Optimization Using Particle Swarm Optimization

December 22, 2013 | | 13 Comments

My research topic for this year was Currency Carry Trade Portfolio Optimization using Particle Swarm Optimization (PSO). In this article I will introduce portfolio optimization and explain why it is important. Secondly, I will demonstrate how particle swarm ... Read More

Algorithmic Trading System Architecture

November 6, 2013 | | 15 Comments

Previously on this blog I have written about the conceptual architecture of an intelligent algorithmic trading system as well as the functional and non-functional requirements of a production algorithmic trading system. Since then I have designed a system architecture ... Read More

Algorithmic Trading System Requirements

October 6, 2013 | | 5 Comments

Currently I am taking a class about software architectures. For this class each student chooses a system, defines its architectural requirements, and designs a solution capable of satisfying those requirements. I chose an algorithmic trading system because of ... Read More

BRICs Economic Forecasting using Neural Networks

September 18, 2013 | | 5 Comments

This weekend I finished an interesting research assignment in which I used five computational techniques to train artificial neural networks to forecast the 2011 GDP growth rates for Brazil, Russia, India, China, and South Africa (BRICS nations). The ... Read More

Measures of Risk-adjusted Return

September 1, 2013 | | 13 Comments

This article is a supplement to some of the topics presented in Dr. Tucker Balch's online MOOC, Computational Investing. Financial markets are complex adaptive systems which are almost always indistinguishable from random processes. That said markets do exhibit quantifiable factors such ... Read More

Perfect Imperfection, Agent Based Models

August 16, 2013 | | 11 Comments

When I was 17 years old the Boy Scouts of America invited nine international delegates and I to present at a conference and partake in a 7-day 100 kilometer hike through the Rocky Mountains on the Philmont Scout Ranch. In the week prior ... Read More

Intelligent Algorithmic Trading Systems

July 7, 2013 | | 7 Comments

Algorithmic trading is the use of computer algorithms to automatically make trading decisions, submit orders, and manage those orders after submission. Algorithmic trading systems are best understood using a simple conceptual architecture consisting of three components which handle different ... Read More

Using Genetic Programming to evolve Trading Strategies

June 3, 2013 | | 22 Comments

A friend and I recently worked together on a research assignment where we successfully used Genetic Programming (GP) to evolve solutions to a real world financial classification problem. This problem, called security analysis, involves determining which securities ought to ... Read More

Clustering using Ant Colony Optimization

April 15, 2013 | | 10 Comments

For many years entomologists have studied the behaviour of ant colonies and marveled at their ability to solve complex problems collectively. An example of this collective intelligence observed by entomologists is that ants leaving their colony will often follow very efficient routes between ... Read More