Data vs. information: using clustering techniques to enhance stock returns forecasting

This paper explores the use of clustering models of stocks to improve both (a) the prediction of stock prices and (b) the returns of trading algorithms. We cluster stocks using k-means and several alternative distance metrics, using as features quarterly financial ratios, prices and daily returns....

Descripción completa

Detalles Bibliográficos
Autores principales:	Vásquez Sáenz, Javier, Quiroga, Facundo Manuel, Fernández Bariviera, Aurelio
Formato:	Articulo
Lenguaje:	Inglés
Publicado:	2023
Materias:	Ciencias Informáticas Stock price forecast Clustering Financial Reports Deep learning Investment algorithms Trading
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/160256
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-160256
record_format	dspace
spelling	I19-R120-10915-1602562023-11-16T20:08:02Z http://sedici.unlp.edu.ar/handle/10915/160256 Data vs. information: using clustering techniques to enhance stock returns forecasting Vásquez Sáenz, Javier Quiroga, Facundo Manuel Fernández Bariviera, Aurelio 2023 2023-11-16T17:56:08Z en Ciencias Informáticas Stock price forecast Clustering Financial Reports Deep learning Investment algorithms Trading This paper explores the use of clustering models of stocks to improve both (a) the prediction of stock prices and (b) the returns of trading algorithms. We cluster stocks using k-means and several alternative distance metrics, using as features quarterly financial ratios, prices and daily returns. Then, for each cluster, we train ARIMA and LSTM forecasting models to predict the daily price of each stock in the cluster. Finally, we employ the clustering-empowered forecasting models to analyze the returns of different trading algorithms. We obtain three key results: (i) LSTM models outperform ARIMA and benchmark models, obtaining positive investment returns in several scenarios; (ii) forecasting is improved by using the additional information provided by the clustering methods, therefore selecting relevant data is an important preprocessing task in the forecasting process; (iii) using information from the whole sample of stocks deteriorates the forecasting ability of LSTM models. These results have been validated using data of 240 companies of the Russell 3000 index spanning 2017 to 2022, training and testing with different subperiods. Instituto de Investigación en Informática Articulo Articulo http://creativecommons.org/licenses/by/4.0/ Creative Commons Attribution 4.0 International (CC BY 4.0) application/pdf
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Stock price forecast Clustering Financial Reports Deep learning Investment algorithms Trading
spellingShingle	Ciencias Informáticas Stock price forecast Clustering Financial Reports Deep learning Investment algorithms Trading Vásquez Sáenz, Javier Quiroga, Facundo Manuel Fernández Bariviera, Aurelio Data vs. information: using clustering techniques to enhance stock returns forecasting
topic_facet	Ciencias Informáticas Stock price forecast Clustering Financial Reports Deep learning Investment algorithms Trading
description	This paper explores the use of clustering models of stocks to improve both (a) the prediction of stock prices and (b) the returns of trading algorithms. We cluster stocks using k-means and several alternative distance metrics, using as features quarterly financial ratios, prices and daily returns. Then, for each cluster, we train ARIMA and LSTM forecasting models to predict the daily price of each stock in the cluster. Finally, we employ the clustering-empowered forecasting models to analyze the returns of different trading algorithms. We obtain three key results: (i) LSTM models outperform ARIMA and benchmark models, obtaining positive investment returns in several scenarios; (ii) forecasting is improved by using the additional information provided by the clustering methods, therefore selecting relevant data is an important preprocessing task in the forecasting process; (iii) using information from the whole sample of stocks deteriorates the forecasting ability of LSTM models. These results have been validated using data of 240 companies of the Russell 3000 index spanning 2017 to 2022, training and testing with different subperiods.
format	Articulo Articulo
author	Vásquez Sáenz, Javier Quiroga, Facundo Manuel Fernández Bariviera, Aurelio
author_facet	Vásquez Sáenz, Javier Quiroga, Facundo Manuel Fernández Bariviera, Aurelio
author_sort	Vásquez Sáenz, Javier
title	Data vs. information: using clustering techniques to enhance stock returns forecasting
title_short	Data vs. information: using clustering techniques to enhance stock returns forecasting
title_full	Data vs. information: using clustering techniques to enhance stock returns forecasting
title_fullStr	Data vs. information: using clustering techniques to enhance stock returns forecasting
title_full_unstemmed	Data vs. information: using clustering techniques to enhance stock returns forecasting
title_sort	data vs. information: using clustering techniques to enhance stock returns forecasting
publishDate	2023
url	http://sedici.unlp.edu.ar/handle/10915/160256
work_keys_str_mv	AT vasquezsaenzjavier datavsinformationusingclusteringtechniquestoenhancestockreturnsforecasting AT quirogafacundomanuel datavsinformationusingclusteringtechniquestoenhancestockreturnsforecasting AT fernandezbarivieraaurelio datavsinformationusingclusteringtechniquestoenhancestockreturnsforecasting
_version_	1807221877166309376

Data vs. information: using clustering techniques to enhance stock returns forecasting

Ejemplares similares