<< back
ReachX logo

Machine learning will change the future of finance

Publication Date: 04 May 2018 - By Market Mogul By Market M.

Macro Multi Asset Financial Services Technology


If one has ever accidentally wasted an hour of their time scrolling through the news feed on Facebook, chances are they have just experienced the power of machine learning. Whether it be facial recognition algorithms used on new smartphones or fraud prevention algorithms used by major credit card companies, machine learning is a technology of the future that has the ability to reshape the financial world forever.

Figure 1

Modern machine learning algorithms use a supervised learning model (Figure 1). This model feeds training data, split into its input data and the known outcomes of those data, into the machine learning algorithm, creating a series of triggers and outputs called a neural network. The result is then manually paired with a label. Once the algorithm is trained with an adequate amount of data, it is used to take new data with an unknown outcome and predict what the outcome will be. Whilst extremely effective for picking out a face in a picture or figuring out which song is playing in the background, neural networks have yet to master more complex financial tasks such as predicting a fluctuation in the stock market.

Forecasting the Network

The vision of research into stock market forecasting is that machine learning algorithms will reach a stage where they can make judgements on stock value direction and magnitude with a success rate that significantly exceeds their running costs. This might seem like an unattainable and unachievable goal, however, with the prospect of a large financial reward, huge amounts of money are being poured into research for this by many financial services companies such as JP Morgan and Morgan Stanley.

Obviously, it’s not that easy to just start up an algorithm and become rich within days. In an extensive investigation, André Anderson, from the Norwegian University of Science and Technology, comes to the conclusion that currently :

“No trading system was able to outperform the [average trader] when using transaction costs.”

Dr Yoshua Bengio, Head of the Montreal Institute for Machine Learning Algorithms said:

“Market inefficiencies tend to be localized in time and ‘space’ (particular markets, with a limited potential volume of profits). So it may well be that some firms have used and are using machine learning but it’s not like [hitting the jackpot], rather like patiently pulling profits here and there, each time with a different specifically tuned model.”

Dr Bengio goes on to say that companies at the moment are using significant amounts of human judgment to assess which trades to make.

Unfortunately, this is the underlying theme with current stock prediction applications using machine learning; the algorithms just are not good enough to exceed the performance of an average speculative trader.

Speculating About the Future

Past systems have used data from news articles to assess specific companies’ success but fail to take into account the virtually random speculative investment playing an important role in driving stock values.

Speculative investment is the process of buying and selling stocks on a short-term basis with little to no evidence for an increase in value over that period. Although counter-intuitive this process, when performed by a significant amount of people, can seriously affect a stock valuation. This is why it is integral to incorporate some sort of detection of popular opinion on companies being traded to even begin to accurately predict their future values.

New, cutting-edge research performed by the Indian Institute of Technology uses sentiment analysis, a process of analysing language in sentences to assess opinion on specific matters. Complex sentiment analysis engines must be able to determine that “that horror movie we watched was so scary” is a positive subjective comment, for example, something that is easy for humans but much more difficult for computers due to the use of contextual language (‘scary’ being positive in this case).

This research uses sentiment analysis on Twitter to assess public opinion of particular companies which can later be fed into the machine learning algorithm. This technique is being employed by many research departments including at Stanford, Cornell and many more.

This, in conjunction with computers’ ability to trawl through billions of words with ease, will enable machine learning algorithms to detect a much much larger spectrum of information ranging from hints of speculative trading on social networks to discussions on trading forums in a way that humans could never do before. If successful, this research will mark a new era for the world of finance.

This post appeared first on The Market Mogul.


Most read