Exploring the use of Big Data techniques for simulating Algorithmic Trading Strategies
Creative Commons CC BY 4.0
In the world of information technology where huge amount of useful information is available and easily accessible, we investigate an approach to utilize this information in Algorithmic Trading. Algorithmic trading involves implementation of a strategy using computer programs to automatically buy and sell financial instruments to generate profit at a speed and frequency that is impossible for a human trader. High Frequency Trading (HFT) is one type of algorithmic trading characterized by high turnover and high order-to-trade ratios. There are different strategies that can be applied to HFT. We propose a framework to utilize information available in the form of news articles, which can be used in stock trading at high frequency. We use semantic values of news articles for different stocks to generate buy/sell signals at a high frequency. We demonstrate the performance of our framework by simulating stock trade based on generated buy/sell signals for a small period of time.