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.

Call and Continuous Trading Mechanisms Under Asymmetric Information: An Experimental Investigation

Abstract: I examine the relative performance of call and continuous auctions under asymmetric information by manipulating trading rules and information sets in laboratory asset markets. I find significant differences in an environment that extends the Kyle (1985) framework to permit the exogenous liquidity trading motive to have a natural economic interpretation. The adverse selection costs incurred by noise traders are significantly lower under the call auction, despite no significant reduction in average price efficiency. This result suggests that discussions of the costs and benefits of insider trading should take place within the context of a specific trading mechanism. UNDERSTANDING THE INFLUENCE of the trading process on the price formation process is a fundamental goal of the large microstructure literature. An important feature of much of this work has been the replacement of the "Walrasian auctioneer" of general equilibrium theory with market makers who stand ready to provide liquidity and immediacy when buy and sell orders are imperfectly synchronized. In this framework, the presence of agents with "inside information" has an important influence on market liquidity and the price formation process. Seminal theoretical works here include Glosten and Milgrom (1985) and Kyle (1985). A primary purpose of this study is to extend this work by examining the behavior of competitive market makers under alternative trading arrangements that differ on the fundamental dimension of whether orders are temporally consolidated prior to execution. The method of inquiry is experimental economics. The two mechanisms I investigate are a call auction, in which all buy and sell orders arriving during a specified interval are batched and executed at a single price, and a continuous auction, in which each buy and sell order is executed upon arrival. Both mechanisms are widely employed. While a call auction is the primary trading mechanism on many continental European stock exchanges, the growing Nasdaq over the counter (OTC) market relies exclusively on a continuous mechanism. In addition, hybrid systems that

Application of evolutionary computation for rule discovery in stock algorithmic trading

Abstract: The first systematic literature review on evolutionary rule discovery in stock algorithmic trading.A clear demonstrate of studies in this field based on a classification framework.A precise analysis of gaps and limitations in existing studies based on detail of evaluation scheme.The most important factors influencing profitability of models are presented in detail.Targeted suggestions for future improvements based on the review are proposed. Despite the wide application of evolutionary computation (EC) techniques to rule discovery in stock algorithmic trading (AT), a comprehensive literature review on this topic is unavailable. Therefore, this paper aims to provide the first systematic literature review on the state-of-the-art application of EC techniques for rule discovery in stock AT. Out of 650 articles published before 2013 (inclusive), 51 relevant articles from 24 journals were confirmed. These papers were reviewed and grouped into three analytical method categories (fundamental analysis, technical analysis, and blending analysis) and three EC technique categories (evolutionary algorithm, swarm intelligence, and hybrid EC techniques). A significant bias toward the applications of genetic algorithm-based (GA) and genetic programming-based (GP) techniques in technical trading rule discovery is observed. Other EC techniques and fundamental analysis lack sufficient study. Furthermore, we summarize the information on the evaluation scheme of selected papers and particularly analyze the researches which compare their models with buy and hold strategy (B&H). We observe an interesting phenomenon where most of the existing techniques perform effectively in the downtrend and poorly in the uptrend, and considering the distribution of research in the classification framework, we suggest that this phenomenon can be attributed to the inclination of factor selections and problem in transaction cost selections. We also observe the significant influence of the transaction cost change on the margins of excess return. Other influenced factors are also presented in detail. The absence of ways for market trend prediction and the selection of transaction cost are two major limitations of the studies reviewed. In addition, the combination of trading rule discovery techniques and portfolio selection is a major research gap. Our review reveals the research focus and gaps in applying EC techniques for rule discovery in stock AT and suggests a roadmap for future research.

Stock market trading rule based on pattern recognition and technical analysis

Abstract: This work provides empirical evidence which confronts the Efficient Market Hypothesis.This work introduces a new definition of the flag pattern.The results show that the trading rule can beat the market.The European market is more inefficient than the US market. This work presents empirical evidence which confronts the classical Efficient Market Hypothesis, which states that it is not possible to beat the market by developing a strategy based on a historical price series.We propose a risk-adjusted profitable trading rule based on technical analysis and the use of a new definition of the flag pattern. This rule defines when to buy or sell, the profit pursued in each operation, and the maximum bearable loss. In order to untie the results from randomness, we used a database comprised of 91,307 intraday observations from the US Dow Jones index. We parameterized the trading rule by generating 96 different configurations and reported the results of the whole sample over 3 subperiods. In order to widen its validity we also replicated the analysis on two leading European indexes: the German DAX and the British FTSE. The returns provided by the proposed trading rule are higher for the European than for the US index, which highlights the greater inefficiency of the European markets.

Social signals and algorithmic trading of Bitcoin

Abstract: The availability of data on digital traces is growing to unprecedented sizes, but inferring actionable knowledge from large-scale data is far from being trivial. This is especially important for computational finance, where digital traces of human behavior offer a great potential to drive trading strategies. We contribute to this by providing a consistent approach that integrates various datasources in the design of algorithmic traders. This allows us to derive insights into the principles behind the profitability of our trading strategies. We illustrate our approach through the analysis of Bitcoin, a cryptocurrency known for its large price fluctuations. In our analysis, we include economic signals of volume and price of exchange for USD, adoption of the Bitcoin technology, and transaction volume of Bitcoin. We add social signals related to information search, word of mouth volume, emotional valence, and opinion polarization as expressed in tweets related to Bitcoin for more than 3 years. Our analysis reveals that increases in opinion polarization and exchange volume precede rising Bitcoin prices, and that emotional valence precedes opinion polarization and rising exchange volumes. We apply these insights to design algorithmic trading strategies for Bitcoin, reaching very high profits in less than a year. We verify this high profitability with robust statistical methods that take into account risk and trading costs, confirming the long-standing hypothesis that trading based social media sentiment has the potential to yield positive returns on investment.

High Frequency Quoting, Trading, and the Efficiency of Prices

Abstract: We examine the relation between high frequency quotation and the behavior of stock prices between 2009 and 2011 for the full cross-section of securities in the U.S. On average, higher quotation activity is associated with price series that more closely resemble a random walk, and significantly lower cost of trading. We also explore market resiliency during periods of exceptionally high low-latency trading: large liquidity drawdowns in which, within the same millisecond, trading algorithms systematically sweep large volume across multiple trading venues. Although such large drawdowns incur trading costs, they do not appear to degrade the price formation process or increase the subsequent cost of trading. In an out-of-sample analysis, we investigate an exogenous technological change to the trading environment on the Tokyo Stock Exchange that dramatically reduces latency and allows co-location of servers. This shock also results in prices more closely resembling a random walk, and a sharp decline in the cost of trading.