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.

Trading Activity and Foreign Exchange Market Quality

Abstract: This paper studies intraday market quality for currency pairs with very different trading characteristics, the Euro-U.S. dollar and the Canadian dollar-U.S. dollar. Two sets of tests - the first based on the ratio of long term to short term variances, and the second based on information spillovers - provide consistent conclusions regarding market quality. The variance ratio analysis shows that market quality is highest for the Euro during European trading and lowest during Asian trading. For the Canadian dollar, market quality is highest during North American trading and lowest during Asian trading. Analysis of information spillovers shows that innovations in returns and volatility for the more heavily-traded Euro predict returns and volatility for the Canadian dollar during Asian and European trading, but innovations for the dollar have predictive power for the Euro during North American trading. Our results suggest that foreign exchange market quality is high, not always when quoting and trading activity are heavy but rather, and somewhat unexpectedly, when activity is not only high, but also geographically focused and concentrated among a limited number of major dealers.

Quantitative Trading: How to Build Your Own Algorithmic Trading Business

Abstract: Preface. Acknowledgments. Chapter 1: The Whats, Whos, and Whys of Quantitative Trading. Who Can Become A Quantitative Trader? The Business Case for Quantitative Trading. Scalability. Demand on Time. The Nonnecessity of Marketing. The Way Forward. Chapter 2: Fishing for Ideas. How to Identify a Strategy That Suits You. Your Working Hours. Your Programming Skills. Your Trading Capital. Your Goal. A Taste for Plausible Strategies and Their Pitfalls. How Does It Compare with a Benchmark and How Consistent Are Its Returns? How Deep and Long is the Drawdown? How Will Transaction Costs Affect the Strategy? Does the Data Suffer from Survivorship Bias? How Did the Performance of the Strategy Change Over the Years? Does the Strategy Suffer from Data-Snooping Bias? Does the Strategy "Fly under the Radar" of Institutional Money Managers? Summary. Chapter 3: Backtesting. Common Backtesting Platforms. Excel. MATLAB. TradeStation. High-End Backtesting Platforms. Finding and Using Historical Databases. Are the Data Split- and Dividend-Adjusted? Are the Data Survivorship Bias Free? Does Your Strategy Use High and Low Data? Performance Measurement. Common Backtesting Pitfalls to Avoid. Look-Ahead Bias. Data-Snooping Bias. Transaction Costs. Strategy Refinement. Summary. Chapter 4: Setting up Your Business. Business Structure: Retail or Proprietary? Choosing a Brokerage or Proprietary Trading Firm. Physical Infrastructure. Summary. Chapter 5: Execution Systems. What an Automated Trading System Can Do for You. Building a Semiautomated Trading System. Building a Fully Automated Trading System. Minimizing Transaction Costs. Testing Your System by Paper Trading. Why Does Actual Performance Diverge from Expectations? Summary. Chapter 6: Money and Risk Management. Optimal Capital Allocation and Leverage. Risk Management. Psychological Preparedness. Summary. Appendix: A Simple Derivation of the Kelly Formula when Return Distribution is Gaussian. Chapter 7: Special Topics in Quantitative Trading. Mean-Reverting versus Momentum Strategies. Regime Switching. Stationarity and Cointegration. Factor Models. What Is Your Exit Strategy? Seasonal Trading Strategies. High-Frequency Trading Strategies. Is it Better to Have a High-Leverage versus a High-Beta Portfolio? Summary. Chapter 8: Conclusion: Can Independent Traders Succeed? Next Steps. Appendix: A Quick Survey of MATLAB. Bibliography. About the Author. Index.

Efficient event processing through reconfigurable hardware for algorithmic trading

Abstract: In this demo, we present fpga-ToPSS (Toronto Publish/Subscribe System Family), an efficient event processing platform for high-frequency and low-latency algorithmic trading. Our event processing platform is built over reconfigurable hardware---FPGAs---to achieve line-rate processing. Furthermore, our event processing engine supports Boolean expression matching with an expressive predicate language that models complex financial strategies to autonomously buy and sell stocks based on real-time financial data.

Classification-based financial markets prediction using deep neural networks

Abstract: Deep neural networks (DNNs) are powerful types of artificial neural networks (ANNs) that use several hidden layers. They have recently gained considerable attention in the speech transcription and image recognition community (Krizhevsky et al., 2012 ) for their superior predictive properties including robustness to overfitting. However their application to algorithmic trading has not been previously researched, partly because of their computational complexity. This paper describes the application of DNNs to predicting financial market movement directions. In particular we describe the configuration and training approach and then demonstrate their application to backtesting a simple trading strategy over 43 different Commodity and FX future mid-prices at 5-minute intervals. All results in this paper are generated using a C++ implementation on the Intel Xeon Phi co-processor which is 11.4x faster than the serial version and a Python strategy backtesting environment both of which are available as open source code written by the authors.

A Tensor-Based Information Framework for Predicting the Stock Market

Abstract: To study the influence of information on the behavior of stock markets, a common strategy in previous studies has been to concatenate the features of various information sources into one compound feature vector, a procedure that makes it more difficult to distinguish the effects of different information sources. We maintain that capturing the intrinsic relations among multiple information sources is important for predicting stock trends. The challenge lies in modeling the complex space of various sources and types of information and studying the effects of this information on stock market behavior. For this purpose, we introduce a tensor-based information framework to predict stock movements. Specifically, our framework models the complex investor information environment with tensors. A global dimensionality-reduction algorithm is used to capture the links among various information sources in a tensor, and a sequence of tensors is used to represent information gathered over time. Finally, a tensor-based predictive model to forecast stock movements, which is in essence a high-order tensor regression learning problem, is presented. Experiments performed on an entire year of data for China Securities Index stocks demonstrate that a trading system based on our framework outperforms the classic Top-N trading strategy and two state-of-the-art media-aware trading algorithms.