Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 4

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  algorithmic trading
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1
100%
EN
In the paper we analyse structural changes in commodity markets, their financialisation and consequently growing automation. The main factors which foster the development of algorithmic trading are explained and the common methods and strategies used in trading processes and required investments in technology reviewed.
PL
Artykuł przedstawia analizę zmian strukturalnych na rynkach towarowych, ich finansyzację, a w konsekwencji zwiększoną automatyzację. Autorka omówiła główne czynniki sprzyjające rozwojowi algorytmicznego handlu, jak również dokonała przeglądu stosowanych metod i strategii optymalizujących proces handlowy i wymagających inwestycji w rozwój technologii.
EN
The aim of the article is to investigate the impact of algorithmic trading on the returns obtained in the context of market efficiency theory. The research hypothesis is that algorithmic trading can contribute to a better rate of return than when using passive investment strategies. Technological progress can be observed in many different aspects of our lives, including investing in capital markets where we can see changes resulting from the spread of new technologies. The methodology used in this paper consists in confronting a sample trading system based on classical technical analysis tools with a control strategy consisting in buying securities at the beginning of the test period and holding them until the end of this period. The results obtained confirm the validity of the theory of information efficiency of the capital market, as the active investment strategy based on algorithmic trading did not yield better results than the control strategy.
EN
The development of High-Frequency Trading since the 1990s has been so dynamic, that one may say it certainly will be present in every country, sooner or later. Most of the research dedicated to High-Frequency Trading is dedicated to show how detrimental it may be to the financial system, other present business models and integration with other entities of the financial market, some try to research how profitable this type of trading may be, and finally some research is dedicated to the risk analysis – although these papers are very limited. This paper is aimed to expand the topic of business models by showing selected strategies of High-Frequency Trading. This is very important since these strategies may be also implemented in conditions of lower liquidity and have a direct influence on the stability of large institutions.
PL
Rozwój handlu o wysokiej częstotliwości, który powstał w latach 90. XX w., jest tak dynamiczny, że można stwierdzić, iż z pewnością będzie obecny w każdym kraju. Większość opracowań poświęconych handlowi o wysokiej częstotliwości można podzielić na: starające się wykazać, jak szkodliwy jest on dla systemu finansowego; opisujące modele biznesowe i współdziałanie z pozostałymi podmiotami rynku finansowego; wykazujące opłacalność handlu i podmiotów stosujących ten rodzaj handlu; poświęcone zagadnieniom zarządzania ryzykiem transakcji o wysokiej częstotliwości, chociaż ich liczba jest bardzo ograniczona. Niniejsze opracowanie ma na celu rozwijać zagadnienia związane z modelami biznesowymi, omawiając wybrane drapieżne techniki w handlu o wysokiej częstotliwości. Jest to dość istotne, ponieważ mogą one być zastosowane w warunkach o niskiej płynności oraz mogą wpływać bezpośrednio na działalność i stabilność pojedynczych, a także znaczących instytucji finansowych.
EN
This study investigates the profitability of an algorithmic trading strategy based on training SVM model to identify cryptocurrencies with high or low predicted returns. A tail set is defined to be a group of coins whose volatility-adjusted returns are in the highest or the lowest quintile. Each cryptocurrency is represented by a set of six technical features. SVM is trained on historical tail sets and tested on the current data. The classifier is chosen to be a nonlinear support vector machine. The portfolio is formed by ranking coins using the SVM output. The highest ranked coins are used for long positions to be included in the portfolio for one reallocation period. The following metrics were used to estimate the portfolio profitability: %ARC (the annualized rate of change), %ASD (the annualized standard deviation of daily returns), MDD (the maximum drawdown coefficient), IR1, IR2 (the information ratio coefficients). The performance of the SVM portfolio is compared to the performance of the four benchmark strategies based on the values of the information ratio coefficient IR1, which quantifies the risk-weighted gain. The question of how sensitive the portfolio performance is to the parameters set in the SVM model is also addressed in this study.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.