This website uses cookies to collect usage information in order to offer a better browsing experience. By browsing this site or by clicking on the "ACCEPT COOKIES" button you accept our Cookie Policy.

Artificial Intelligence & Machine Learning in Trading

QuantInsti

Contributor:
QuantInsti
Visit: QuantInsti

Excerpt

What is Artificial Intelligence and how is it Used in Trading?

Basically, Artificial Intelligence (AI) is the science and engineering of making intelligent machines. Specifically, it takes into account intelligent computer programs to calculate, reason, learn from experience, adapt to new situations and solve complex problems. Artificial Intelligence (AI) is mainly based on disciplines such as Computer Science, Psychology, Linguistics, Mathematics, Biology and Engineering.


Types of Artificial Intelligence

Now, you must know that both Rules-Based Systems and Machine Learning help to infer the input data. Both types are individually important for particular situations. Now let us see how these types are different from each other.

Rules-Based Systems

Rules-Based Systems are considered the simple kind of Artificial Intelligence. They only need to be fed with the statements that comply with either THIS or THAT for making the system come to a conclusion. Hence, it consists of some IF-THEN rules along with a set of facts. There are two main principles it functions on, which are:

  • A set of facts
  • A set of rules

A set of facts

These are the set of general facts on which the data depends. For instance, the price of a book is INR 100 or is more than INR 100.

A set of rules

These are the engines for facts since they decide what the outcome will be in both cases of facts. For example, if the price of the book is 10$ then you buy it.

So, since you are clear with both the concepts, let us see another example. The AI is fed with the rules-based information to recommend which colour of shoes to wear every day. In this scenario, there will be facts supporting the same. The facts can differ for several reasons that particular day, like:

  • It is raining
  • It is a sports day
  • It is a celebration day

Based on the facts above, the system will conclude each day accordingly.

Here, it is also important to note that the decisions are fed to the system with the help of a group of human experts in the particular field.

Also, rules are easy to write since you need only an addition of a rule to be given to the system in case of any additional fact in the decision-making process that you did not consider earlier. Another important point to note here is that the rules are deterministic and hence, not putting the rules in place appropriately can lead to false outcomes. Moreover, there can be occasions where changes in real-life scenarios may be faster than updates in the system. This also can make the outcomes faulty.

To read more, you can refer to the research paper here.

Machine Learning

Machine Learning is another approach but an improved one which helps to do away with the issues in Rules-Based Systems. In this, the machine is fed with information about the outcome of each data point and not the decision-making process.

For instance, in case the scholarship applications were refused for some applicants out of 1000, then the system will only feed the outcome and not the entire process.

This way, the automated system learns to make more accurate decisions as compared to Rules-Based Systems.

Hence, it operates on the basis of historic outcomes and predicts what future outcome can be. Also, apart from the historic outcomes, it takes into consideration other parameters or factors impacting the decision.

According to another example, the output here can be something as simple as ‘Whether I should carry an umbrella today or not?’. Hence, there can be as many input variables or features as required. Although the input variables and outputs are very much the real-world scenarios, it still becomes difficult to explain the several factors playing a role in between.

Let us now see where the machine learning process may not work.

Here, an example can be helping to decide the attire for an occasion. In such a case, there are so many factors affecting the decision, and one of them is the ‘temperature on a particular day’. The system will check the temperature on the same day a year ago to base its outcome on.

But, here the factor may be not aligned. It is so because on a particular day this year, the temperature may be more or less. And hence, to decide according to the current temperature, the system will have to depend on the facts of that day.

It is also important to mention that Machine Learning also has a ‘Decision tree’ method which resembles Rule-Based Systems. In this, you need to feed the system with a single statement at the start and follow through the decisions made later. But, there is a difference between the Decision tree and Rules-Based system which is with the information fed. The Rules-Based system comes via input from human experts, whereas, the decisions in a Decision tree are made by the machine learning process.

Now, as you are clear about the types of Artificial Intelligence, let us move ahead and find out the Impact of Artificial Intelligence and Machine Learning on Trading.

Read the rest of the article on QuantInsti blog:
https://blog.quantinsti.com/artificial-intelligence-machine-learning-trading/

Disclosure: Interactive Brokers

Information posted on IBKR Traders’ Insight that is provided by third-parties and not by Interactive Brokers does NOT constitute a recommendation by Interactive Brokers that you should contract for the services of that third party. Third-party participants who contribute to IBKR Traders’ Insight are independent of Interactive Brokers and Interactive Brokers does not make any representations or warranties concerning the services offered, their past or future performance, or the accuracy of the information provided by the third party. Past performance is no guarantee of future results.

This material is from QuantInsti and is being posted with permission from QuantInsti. The views expressed in this material are solely those of the author and/or QuantInsti and IBKR is not endorsing or recommending any investment or trading discussed in the material. This material is not and should not be construed as an offer to sell or the solicitation of an offer to buy any security. To the extent that this material discusses general market activity, industry or sector trends or other broad based economic or political conditions, it should not be construed as research or investment advice. To the extent that it includes references to specific securities, commodities, currencies, or other instruments, those references do not constitute a recommendation to buy, sell or hold such security. This material does not and is not intended to take into account the particular financial conditions, investment objectives or requirements of individual customers. Before acting on this material, you should consider whether it is suitable for your particular circumstances and, as necessary, seek professional advice.

trading top