Articles producció científica> Gestió d'Empreses

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

  • Dades identificatives

    Identificador: imarina:9295899
    Autors:
    Saenz, JVQuiroga, FMBariviera, AF
    Resum:
    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.
  • Altres:

    Autor segons l'article: Saenz, JV; Quiroga, FM; Bariviera, AF
    Departament: Gestió d'Empreses
    Autor/s de la URV: Fernández Bariviera, Aurelio
    Paraules clau: Trading Stock price forecast Investment algorithms Financial reports Deep learning Clustering
    Resum: 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.
    Àrees temàtiques: Matemática / probabilidade e estatística Interdisciplinar Finance Engenharias iv Engenharias iii Economics and econometrics Economia Direito Ciencias sociales Business, finance Administração, ciências contábeis e turismo Administração pública e de empresas, ciências contábeis e turismo
    Accès a la llicència d'ús: https://creativecommons.org/licenses/by/3.0/es/
    Adreça de correu electrònic de l'autor: aurelio.fernandez@urv.cat
    Identificador de l'autor: 0000-0003-1014-1010
    Data d'alta del registre: 2024-08-03
    Versió de l'article dipositat: info:eu-repo/semantics/publishedVersion
    URL Document de llicència: https://repositori.urv.cat/ca/proteccio-de-dades/
    Referència a l'article segons font original: International Review Of Financial Analysis. 88 102657-
    Referència de l'ítem segons les normes APA: Saenz, JV; Quiroga, FM; Bariviera, AF (2023). Data vs. information: Using clustering techniques to enhance stock returns forecasting. International Review Of Financial Analysis, 88(), 102657-. DOI: 10.1016/j.irfa.2023.102657
    DOI de l'article: 10.1016/j.irfa.2023.102657
    Entitat: Universitat Rovira i Virgili
    Any de publicació de la revista: 2023
    Tipus de publicació: Journal Publications
  • Paraules clau:

    Business, Finance,Economics and Econometrics,Finance
    Trading
    Stock price forecast
    Investment algorithms
    Financial reports
    Deep learning
    Clustering
    Matemática / probabilidade e estatística
    Interdisciplinar
    Finance
    Engenharias iv
    Engenharias iii
    Economics and econometrics
    Economia
    Direito
    Ciencias sociales
    Business, finance
    Administração, ciências contábeis e turismo
    Administração pública e de empresas, ciências contábeis e turismo
  • Documents:

  • Cerca a google

    Search to google scholar