Machine learning has already helped a lot to solve complex problems in the domain of natural language processing, image and speech recognition, etc. Recently, deep learning or neural networks have emerged as one of the most popular and powerful methods for learning tasks. The financial sector is also not left untouched by the current wave of machine learning and artificial intelligence.
The present financial market is already comprised of humans as well as machines. There are machines out there doing trades of billions of dollars every day in a response time measured in microseconds popularly known as high-frequency trading. According to stats, nearly 73% of the everyday trading is executed by machines. Every major financial firm is investing in algorithmic trading because the level and volume of trade carried out by these machines is out of human bounds to process and execute. Based on a very complex model, these machines take into account the past historical financial data available as well as other information available on the internet such as news. These systems make real-time trade decisions that maximize their returns
Flooded as the market is with such artificial trading systems, the market is becoming more and more sophisticated day by day. These systems compete in real-time for trading, and as part of these competitions, these systems often indulge in flooding the market with false data to slow down competitors and get an edge over them. Also, there might be times when algorithm may behave abnormally. One of the famous examples is the Flash Crash of 2010, where the market fell down abruptly and recovered in a short span of 36 minutes.
Now, from a machine learning perspective, active research is going on in the field of stock trading, portfolio optimization, etc. Researchers are constantly trying to learn more and more information from the large volume of data available. Older models used only the numerical data available, but today’s system takes into account the financial news before it even reaches humans and infers outcomes based on the news. In the future, we can expect machines to have greater control over the financial markets.
Above is another good Ted Talk on algorithmic trading and use of machine learning in finance.