Geekly Articles each Day
📜 ⬆️ ⬇️

What's New: 3 technological trends in algorithmic trading



In our blog, we pay great attention to the issues of algorithmic trading and offer a number of technological solutions for its implementation (for example, direct access to the exchange ).

A few months ago, the presentation of IKnowFirst financial service founder Lipa Roitman and project manager Yaron Golgher about trends and trends in algorithmic trading was published. We present to you the main thoughts from this document.

News Analysis


Currently, many algorithmic traders are working on developing systems for analyzing and interpreting news in order to extract information on the basis of which a trading robot could perform transactions. (On the impact of news on the market, we wrote in this material ).
')
For receiving news, various services are used - for example, Google Trends, which shows the popularity of a particular search query. Algorithms also analyze news feeds (for example, Thomson Reuters, Bloomberg, etc.).

Moreover, the authors of the presentation point to the possibility of developing systems that would automatically create articles on news from such tapes and then publish them on the network — in this way one can provoke to buy or sell a human trader who does not have access to news feeds and receives information with some delay.

Machine learning


For the analysis of markets used mathematical, statistical and logical tools. With their help, it is possible to create hypotheses that can be tested (for example, on historical data).

The process of machine learning consists of several steps from the selection of mathematical and software tools, copying input data, to generating predictions and optimizing their accuracy.



It is hardly possible to use only this tool for creating a truly effective strategy, however, as the experiment showed, which we wrote about in our blog earlier , the use of machine learning and historical data allows you to create strategies that will generate a certain income.

Genetic algorithms


There are a number of search algorithms, one of which is genetic . It is used to solve complex problems, in cases where the exact relationship between the elements involved is unknown and may not exist in principle.

The task is formalized so that its solution can be encoded as a vector of genes (“genotype”), where each gene can represent a bit, a number, or some other object. Further, a set of genotypes of the initial “population” is randomly created, which are estimated using a special fitness function.



As a result, each genotype is assigned the value of "fitness" - it determines how well it solves the problem.

Other materials on algorithmic trading from ITinvest:

Source: https://habr.com/ru/post/269761/

More articles:


All Articles