A Bottom-up Approach to the Financial Markets: Agent-Based Quantitative Algorithmic Strategies: Ecosystem, Dynamics & Detection

Abstract

In this paper we propose a new approach to studying the financial markets. Instead of the traditional top- down approach where a Brownian Motion is assumed as the main driving force behind the market movement (and where dynamic strategies are built as a result), we rather take the opposite point of view (the bottom-up approach) by assuming that it is the interaction of systematic strategies that induces the dynamics of the market. We achieve this shift in perspective, by re-introducing the High Frequency Trading Ecosystem (HFTE) model. More specifically we specify an approach in which agents interact through a Neural Network structure designed to address the complexity demands of most common financial strategies but designed randomly at inception. This strategy ecosystem is then studied through a simplified genetic algorithm. Taking an approach in which simulation and hypothesis interact in order to improve the theory, we explore areas that are usually associated to fields orthogonal to Quantitative Finance such as Evolutionary Dynamics & predator-prey models. We introduce in that context concepts such as the Path of Interaction in order to study our Ecosystem of strategies through time. Finally a Particle Filter methodology is then proposed to track the market ecosystem through time.

Keywords: High Frequency Trading Ecosystem (HFTE), High Frequency Financial Funnel (HFFF), Multi-Target Tracking (MTT), Stability of Financial Systems, Markov Chain Monte Carlo (MCMC), Data Analysis and Patterns in Data, Electronic Trading, Systemic Risk, High Frequency Trading, Game Theory, Machine Learning