In this work we present an Artificial Neural Network (ANN) approach to predict stock market indices.In particular, we focus our attention on their trend movement up or down. We provide results of experimentsexploiting different Neural Networks architectures, namely the Multi-layer Perceptron (MLP), the ConvolutionalNeural Networks (CNN), and the Long Short-Term Memory (LSTM) recurrent neural networks technique. Weshow importance of choosing correct input features and their preprocessing for learning algorithm. Finally we testour algorithm on the S&P500 and FOREX EUR/USD historical time series, predicting trend on the basis of datafrom the past n days, in the case of S&P500, or minutes, in the FOREX framework. We provide a novel approachbased on combination of wavelets and CNN which outperforms basic neural networks approaches.

Artificial Neural Networks Approach to the Forecast of Stock Market Price Movements

DI PERSIO, Luca
;
HONCHAR, OLEKSANDR
2016

Abstract

In this work we present an Artificial Neural Network (ANN) approach to predict stock market indices.In particular, we focus our attention on their trend movement up or down. We provide results of experimentsexploiting different Neural Networks architectures, namely the Multi-layer Perceptron (MLP), the ConvolutionalNeural Networks (CNN), and the Long Short-Term Memory (LSTM) recurrent neural networks technique. Weshow importance of choosing correct input features and their preprocessing for learning algorithm. Finally we testour algorithm on the S&P500 and FOREX EUR/USD historical time series, predicting trend on the basis of datafrom the past n days, in the case of S&P500, or minutes, in the FOREX framework. We provide a novel approachbased on combination of wavelets and CNN which outperforms basic neural networks approaches.
File in questo prodotto:
File Dimensione Formato  
Artificial Neural Networks Approach to the Forecast of Stock Market Price Movements.pdf

accesso aperto

Tipologia: Versione dell'editore
Licenza: Dominio pubblico
Dimensione 753.7 kB
Formato Adobe PDF
753.7 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11562/945382
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact