Algorithmic trading

About: Algorithmic trading is a research topic. Over the lifetime, 6718 publications have been published within this topic receiving 162209 citations. The topic is also known as: algotrading & Algorithmic trading.

Intraday relationships among index arbitrage, spot and futures price volatility, and spot market volume: A transactions data test☆

Abstract: This paper examines intraday temporal relationships among arbitrage spreads, cash and futures price volatility, and cash trading volume, using transactions data for the Major Market Index futures contracts and the component stocks of the index. Results indicate that changes in the spread have a significant impact on cash and futures price volatility as well as on cash trading volume. The impact of the spread, however, is attenuated by the short-sale restriction in the cash market. Contrary to popular beliefs, a more volatile market leads to subsequent decreases in the spread, probably because of increases in the supply of arbitrage services or faster price adjustments.

The global financial markets: an ultra-large-scale systems perspective

Abstract: We argue here that, in recent years, the world's financial markets have become a globally interconnected complex adaptive ultra-large-scale socio-technical system-of-systems, and that this has important consequences for how the financial markets should be engineered and managed in future. Major failures in the financial markets can now occur at super-human speeds, as was witnessed in the "Flash Crash" of May 6th 2010. Events such as the Flash Crash may become more commonplace in future, unless lessons are learned from other fields where complex adaptive socio-technical systems-of-systems have to be engineered for high-integrity, safety-critical applications. In this document we review the literature on failures in risky technology and high-integrity approaches to safety-critical SoS engineering. We conclude with an argument that, in the specific case of the global financial markets, there is an urgent need to develop major national strategic modeling and predictive simulation capabilities, comparable to national-scale meteorological monitoring and modeling capabilities. The intent here is not to predict the price-movements of particular financial instruments or asset classes, but rather to provide test-rigs for principled evaluation of systemic risk, estimating probability density functions over spaces of possible outcomes, and thereby identifying potentially high-consequence failure modes in the simulations, before they occur in real life, by which time it is typically too late.

Designing safe, profitable automated stock trading agents using evolutionary algorithms

Abstract: Trading rules are widely used by practitioners as an effective means to mechanize aspects of their reasoning about stock price trends. However, due to the simplicity of these rules, each rule is susceptible to poor behavior in specific types of adverse market conditions. Naive combinations of such rules are not very effective in mitigating the weaknesses of component rules. We demonstrate that sophisticated approaches to combining these trading rules enable us to overcome these problems and gainfully utilize them in autonomous agents. We achieve this combination through the use of genetic algorithms and genetic programs. Further, we show that it is possible to use qualitative characterizations of stochastic dynamics to improve the performance of these agents by delineating safe, or feasible, regions. We present the results of experiments conducted within the Penn-Lehman Automated Trading project. In this way we are able to demonstrate that autonomous agents can achieve consistent profitability in a variety of market conditions, in ways that are human competitive.