Forecasting Price Movements in Betting Exchanges Using Cartesian Genetic Programming and ANN

Abstract

Since the introduction of betting exchanges in 2000, there has been increased interest of ways to monetize on the new technology. Betting exchange markets are fairly similar to the financial markets in terms of their operation. Due to the lower market share and newer technology, there are very few tools available for automated trading for betting exchanges. The in-depth analysis of features available in commercial software demonstrates that there is no commercial software that natively supports machine learned strategy development. Furthermore, previously published academic software products are not publicly obtainable. Hence, this work concentrates on developing a full-stack solution from data capture, back-testing to automated Strategy Agent development for betting exchanges. Moreover, work also explores ways to forecast price movements within betting exchange using new machine learned trading strategies based on Artificial Neuron Networks (ANN) and Cartesian Genetic Programming (CGP). Automatically generated strategies can then be deployed on a server and require no human interaction. Data explored in this work were captured from 1st of January 2016 to 17th of May 2016 for all GB WIN Horse Racing markets (total of 204GB of data processing). Best found Strategy agent shows promising 83% Return on Investment (ROI) during simulated historical validation period of one month (15th of April 2016 to 16th of May 2016).

"Implementing the BBE Agent-Based Model of a Sports-Betting Exchange"

“…In comparison, the number of research papers reporting on in-play betting is small: as is discussed in more detail in Cli (2021), the publications of Easton and Uylangco (2009); Tsrimpas (2015) and Dzalbs and Kalganova (2018) each o er the possibility of exploring in-play betting but either choose not to, or are reporting on systems that are not public-domain open-source SDGs, and hence unlike BBE.…”

BBE: Simulating the Microstructural Dynamics of an In-Play Betting Exchange via Agent-Based Modelling

“…The comprehensive PhD thesis by Tsrimpas (2015) presents a betting optimization system called Sportsbet, and an associated domain-specific programming language called Ubel, which are demonstrated in use for in-play football and tennis matches, and also for ex-ante betting on horse-races, working on both historical and real-time data fed from Betfair: there seems no reason to doubt that Sportsbet could be used for refining betting strategies for in-play betting on race events, but none are reported by Tsrimpas (2015); unlike BBE it cannot act as a synthetic data generator (SDG) because it was not designed to do so, and it is not available as an open-source research tool. Similarly, the system described by Dzalbs and Kalganova (2018) seems to have the capability to operate on in-play data, but the strategies that are developed in that paper are all dedicated on placing bets before the start of the race; and, like Sportsbet, it is neither an SDG nor an open-source research tool.…”

Forecasting Stock Exchange Data using Group Method of Data Handling Neural Network Approach

“…Variational Mode Decomposition and entropy theory was proposed to forecast exchange rates [32]. Dzalbs et al proposed Cartesian Genetic Programming and artificial neural network (ANN), and Amat et al presented simple machine learning methods for forecasting exchange rates [33]. The methods they used were sequential ridge regression and the exponentially weighted average strategy.…”