Faculty Advisor

Hakim, Hossein

Faculty Advisor

Ludwig, Reinhold

Faculty Advisor

Somasse, Gbetonmasse Blaise

Abstract

In financial trading, emotion can often obstruct clear decision making. The goal of this project is to build a system which can overcome this by trading foreign currencies autonomously. Three systems were created: two relying on neural networks, and a third on pattern recognition of candlestick charts. A fourth system has been designed to allocate funds to the others using utility theory. Though the algorithms were not profitable, a powerful interface was built, connecting Python scripts to MetaTrader 4 for trading.

Publisher

Worcester Polytechnic Institute

Date Accepted

April 2019

Project Type

Interactive Qualifying Project

Accessibility

Unrestricted

Share

COinS