Electronic Trading & Machine Learning

The rise of computer & data storing technologies, have given birth to the area of research commonly known as Machine Learning and more broadly speaking Artificial Intelligence.

Like many new scientific fields, its novelty associated with its early industry adoptions has led to much creativity but also a lot of misuse which EQRC has been specializing in exposing and presenting alternative solutions for. More specifically EQRC has been specializing in backtesting methodologies as well as exposing through the weighing of the probabilities whether a signal has legitimate value or whether we are dealing with a signal with apophenic potentially.

The electric signals dancing about in the dendrites bridging neurone is the core inspirational root for the area of Machine Learning, and therefore the reason why the picture on the left was chosen for this section.

More specifically most of the learning algorithm have an a-priory distribution which posterior is refined through observation. In the case of the neurone, the algorithm that best describes this iterative process is one in which the error in between the forecast and the observation is back-propagated in the neural network architecture which complexity determines the speed and the extend at which the algorithm can learn a particular problem just enough to make an accurate forecast consistently.

The Backtesting Phases

EQRC has great deal of practical experience with a strong theoretical foundation as laid out by some of our publications. Backtesting can be very roughly summarised in 4 steps:
1

backtesting 1st phase

The first phase of any backtesting exercise is the hypothesis specification and the determined time and ressource investment to properly test this hypothesis.

3

backtesting second phase

The second phase of a backtesting exercise is to investigate quality of data. That by itself can be a tedious stask which is nevertheless necessary.

4

3rd backtesting phase

The 3rd phase consists of the hands on programer getting locked into the exercise in which cost of strategy along with proper simulation are performed.

2

4th backtesting phase

Before potential deployment, it is important to analyse to what extend the results of the backtest correspond to the hypothesis from first phase.

Deep Learning and Pattern Recognition

HFTE: We propose in this model that the oscillations of the HF markets are due to the interactions of the different strategies designed by the market participants. More specifically, we propose that these oscillations are of the same nature as the Lotka Volterra model. In order to test our hypothesis we have proposed a topology which we proved is able to model the HFT strategies known to the market participants. More specifically we have illustrated how it can achieve the Trend Following, the MLR and the XOR strategies. This topology is then randomly sampled at inception (the random seed) in this swarm market and a simple genetic algorithm is enforced to allow us to study the market and its participants through time. The results are commensurate with the Lotka Volterra model as well as some of the other Game Theory results, more specifically around strategy invasion that we have also made a comparison to (relevant paper to appear in Wilmott magazine in May 2017).

UTOPE: The financial industry is at the heart of our economy and fittingly comes under much scrutiny. Indeed, as a result of social and political pressure, particularly since the recent subprime crisis, more rigorous regulations have been imposed on both “authorized firms” and “approved persons” via the SEC and the FSA. It is hoped that these restrictions will continue to secure fair and honest practices within the industry, as well as restoring the public’s confidence in bankers. This article will outline one risk that institutions like the SEC and the FSA have not regulated heavily enough but must address promptly if trust in them is to be preserved. This is the Unfortunate cosT Of Pattern rEcognition (UTOPE), technically known as apophenia.

Backtesting Expertise

Wether it is for strategy building or for decipher pattern for any purposed, the backtesting exercise is currently sold in the scientific community almost as an exact science however backtesting when it comes to Financial Strategies is an open problem in quantitative Finance which does require a lot of human and computer interaction.

John F. Kennedy would describe us as the most extraordinary computer of all. However this claim with the co-arrival of Big Data and advances in the field of applied probability, statistic & pattern recognition is currently under siege for many applications that EQRC is focusing on.

These projects are usually highly confidential and unique in design. Please contact us for more information.

“UTOPE-ia”.
download

“Presentation on the HFTE model and UTOPE-ia concepts.”
download

Thank you for your interest

 Stable Match is currently in testFlight. Please contact us if you are interested in the app. We will send you the appropriate instruction.