Reinforcement learning for algorithmic trading on financial markets

Suciu, Claudia Maria (2017) Reinforcement learning for algorithmic trading on financial markets. Masters thesis, Dublin, National College of Ireland.

Preview

PDF (Master of Science) Download (1MB) | Preview

Abstract

Can algorithmic trading learn to trade efficiently by itself, given risk and preference parameters are provided? Financial markets pose increasing challenges in speed and lower fees making difficult trades in the traditional manner with a satisfactory return. Self learning systems can provide a viable option as standalone trader in the current challenging finance trading environment and big data flow. Wide adoption of algorithmic trading has rooted out some of the market inefficiencies that represent profit opportunities for speculators.Uncorrelated portfolios and market making had left little choice to traditional trader, but to look for a continuous automation and optimization. Recurrent neural networks have still major contributions to make for the stability of the financial market and exploitation of its inefficiencies.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Financial Services
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Caoimhe Ní Mhaicín
Date Deposited:	27 Aug 2018 14:02
Last Modified:	27 Aug 2018 14:03
URI:	https://norma.ncirl.ie/id/eprint/3075

Actions (login required)

View Item