Using Machine Learning Methods in Financial Market for Fundamental or Technical Analysis Based on Hybrid Models

Please enable javascript in your browser.

Sabbaghi Lalimi, Amir Hossein | 2020

444 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 52644 (01)
University: Sharif University of Technology
Department: Industrial Engineering
Advisor(s): Kianfar, Farhad
Abstract:
Forex prediction is one of the inresting topics for researchers and traders. They are always trying to improve their accuracy. Recently machine learning technichs especially deep neural networks has shown great success and high accuracy for market prediction.In this paper we propose several multi-input deep neural networks to predict the direction and amount of change for euro/usd rate. Our models are based on scalping strategy fitting high frequency trading. Our first model is based on deep Long Short Term Memory layers which is our best model. Our second model is based on deep 1D- Convolutional layers. The last model is our simplest model which is based on MultiLayer Perceptron. Also we built a majority voting ensemble model based on our three deep neural network. The results show that the Long Short Term Memory-based multi-input model reach over win rate on scalping strategy. This means that this model can empower the trader to win over on a high frequency trading strategy
Keywords:
Machine Learning ; Deep Learning ; Long Short Term Memory (LSTM) ; Neural Network ; Convolutional Neural Network ; Multi-Layer Perceptron (MLP) ; Forex Prediction

No TOC