Published Paper Details:

The objective of this research is to analyze the impact of artificial intelligence on algorithmic trading. Given the complexity of modern markets, it is near impossible to isolate the impact of individual market participants due to the countless interactions/trades that occur throughout the market's lifespan. The scope of this paper is to address the new emerging as well as existing techniques of AI in algorithmic trading. This paper tries to understand the impact of AI on algorithmic trading using observations and results from the research conducted. This paper broadly covers the types of trading and advantages of algorithmic trading. It also explains how AI has been implemented in algorithmic trading techniques to enhance the profit making model. In the due course, various AI techniques have been explained which has provided an insight to AI readers about how complex and simple AI techniques have been helpful to predict the financial markets. Quantitative momentum investment strategies were first brought to the forefront in 1994 by Jegadeesh and Titman, who showed the efficacy of relative strength in the United States. A few years later, in 1997, Hsu, Myers, and Baesel conducted a study to test whether a simple moving average strategy would result in abnormal returns after transaction costs [1]. The results of the study, as expected, strongly suggested that the performance of these investment strategies was dependent on the frequency at which the portfolios are rebalanced. Given that moving average rules are trend-following in nature and are best suited for trending markets. These strategies differ greatly from the more traditional ones used by pension funds, in that they typically seek to produce returns that are uncorrelated with the major asset classes, with moderate to high levels of risk[1,2]. With the success of these strategies, a framework for evaluating and comparing quantitative investment strategies is imperative to provide the basis for selecting between them.