Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Evolution of the IBEX-35 vs other international indices: determinants of market value according to XGBOOST and GLM models

Evolution of the IBEX-35 vs other international indices: determinants of market value according... The purpose of this paper is to study the influence of different quantitative (traditionally used) and qualitative variables, such as the possible negative effect in determined periods of certain socio-political factors on share price formation.Design/methodology/approachWe first analyse descriptively the evolution of the Ibex-35 in recent years and compare it with other international benchmark indices. Bellow, two techniques have been compared: a classic linear regression statistical model (GLM) and a method based on machine learning techniques called Extreme Gradient Boosting (XGBoost).FindingsXGBoost yields a very accurate market value prediction model that clearly outperforms the other, with a coefficient of determination close to 90%, calculated on validation sets.Practical implicationsAccording to our analysis, individual accounts are equally or more important than consolidated information in predicting the behaviour of share prices. This would justify Spain maintaining the obligation to present individual interim financial statements, which does not happen in other European Union countries because IAS 34 only stipulates consolidated interim financial statements.Social implicationsThe descriptive analysis allows us to see how the Ibex-35 has moved away from international trends, especially in periods in which some relevant socio-political events occurred, such as the independence referendum in Catalonia, the double elections of 2019 or the early handling of the Covid-19 pandemic in 2020.Originality/valueCompared to other variables, the XGBoost model assigns little importance to socio-political factors when it comes to share price formation; however, this model explains 89.33% of its variance. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Academia Revista Latinoamericana de Administración Emerald Publishing

Evolution of the IBEX-35 vs other international indices: determinants of market value according to XGBOOST and GLM models

Download PDF
22 pages

Loading next page...
 
/lp/emerald-publishing/evolution-of-the-ibex-35-vs-other-international-indices-determinants-69Y4BcNtrx
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1012-8255
DOI
10.1108/arla-06-2021-0124
Publisher site
See Article on Publisher Site

Abstract

The purpose of this paper is to study the influence of different quantitative (traditionally used) and qualitative variables, such as the possible negative effect in determined periods of certain socio-political factors on share price formation.Design/methodology/approachWe first analyse descriptively the evolution of the Ibex-35 in recent years and compare it with other international benchmark indices. Bellow, two techniques have been compared: a classic linear regression statistical model (GLM) and a method based on machine learning techniques called Extreme Gradient Boosting (XGBoost).FindingsXGBoost yields a very accurate market value prediction model that clearly outperforms the other, with a coefficient of determination close to 90%, calculated on validation sets.Practical implicationsAccording to our analysis, individual accounts are equally or more important than consolidated information in predicting the behaviour of share prices. This would justify Spain maintaining the obligation to present individual interim financial statements, which does not happen in other European Union countries because IAS 34 only stipulates consolidated interim financial statements.Social implicationsThe descriptive analysis allows us to see how the Ibex-35 has moved away from international trends, especially in periods in which some relevant socio-political events occurred, such as the independence referendum in Catalonia, the double elections of 2019 or the early handling of the Covid-19 pandemic in 2020.Originality/valueCompared to other variables, the XGBoost model assigns little importance to socio-political factors when it comes to share price formation; however, this model explains 89.33% of its variance.

Journal

Academia Revista Latinoamericana de Administración – Emerald Publishing

Published: Feb 14, 2022

Keywords: Ibex-35; Book value; Market value; Prediction models; Extreme gradient boosting; C53; D53; E65; F17; G15; M41; Ibex-35; valor contable; valor de mercado; modelos de predicción; Extreme gradient boosting

References

  • Utilidad de la información contable para evaluar la rentabilidad de sociedades dominantes: papel de la información consolidada frente a la individual
    Ansón, J.A.; Brusca, M.P.; Brusca, M.I.
  • An empirical evaluation of accounting income numbers
    Ball, R.; Brown, P.
  • Predicting failure in the U.S. banking sector: an extreme gradient boosting approach
    Carmona, P.; Climent, F.; Momparler, A.
  • Fundamentals and stock returns in Japan
    Chan, L.K.; Hamao, Y.; Lakonishok, J.
  • XGBoost: a scalable tree boosting system
    Chen, T.; Guestrin, C.
  • Anticipating bank distress in the Eurozone: an Extreme gradient boosting approach
    Climent, F.; Momparler, A.; Carmona, P.
  • El análisis contable y el mercado de capitales: Un estudio empírico acerca de la relación entre la información contable y los precios de las acciones
    Crespo, M.A.
  • Politics and the stock market: evidence from Germany
    Döpke, J.; Pierdzioch, C.
  • Agregate accounting earnings can explain most of security returns
    Easton, P.; Harris, T.; Ohlson, J.
  • Greedy function approximation: a gradient boosting machine
    Friedman, J.H.
  • Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors)
    Friedman, J.; Hastie, T.; Tibshirani, R.
  • Relevancia de las magnitudes contables en la valoración de mercado de las acciones: Un estudio empírico de las características de las empresas cotizadas
    Gallizo, J.L.; Andrés, E.; Salvador, M.
  • Determinantes de la relación entre el precio y el valor contable de las acciones
    Garcia, M.; Rueda, J.A.
  • Factores determinantes del ratio Book-to-Market
    Laínez, G.J.A.; Cuéllar, F.B.
  • h2o: R interface for the ‘H2O' Scalable machine learning platform
    LeDell, E.; Gill, N.; Aiello, S.; Fu, A.; Candel, A.; Click, C.; Kraljevic, T.; Nykodim, T.; Aboyoun, P.; Kurka, M.; Malohlava, M.
  • Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction
    Maciej Zięba, M.; Tomczak, S.K.; Tomczak, J.M.
  • Determinantes fundamentales de la rentabilidad de las acciones
    Menéndez, S.
  • Existe relación entre la información contable y el riesgo sistemático de las empresas?: estimación con datos panel
    Menéndez, C.; Orgaz, N.; Prior, D.
  • Factores determinantes del valor bursátil de las empresas portuguesas (1991–1999). Nuevas propuestas metodológicas
    Miralles, J.L.; Miralles, J.L.
  • Factores que influyen en las acciones sustentables de la Bolsa Mexicana de Valores
    Morales, J.A.
  • Valor bursátil de los bancos europeos: determinantes económico-financieros y de gobierno corporativo
    Muñoz, I.; Fernández, M.R.
  • Generalized linear models
    Nelder, J.; Wedderburn, R.
  • Presidential Elections and the stock market
    Niederhoffer, V.; Gibbs, S.; Bullock, J.
  • Earnings, bookvalues and dividends in equity valuation
    Ohlson, J.A.
  • Disaggregated accounting data as exploratory variables for retuns
    Ohlson, J.A.; Penman, S.H.
  • Impacto de expectativas políticas en los retornos del Índice General de la Bolsa de Valores de Lima
    Rodríguez, G.; Vargas, A.
  • La formación de precios de las acciones alrededor del pago de dividendos en el mercado de capitales español
    Ruiz, F.J.; Espitia, M.
  • Experimenting XGBoost algorithm for prediction and classification of different datasets
    Santhanam, R.; Uzir, N.; Raman, S.; Banerjee, S.
  • The impact of relevant international factors on the returns of Ibex 35 companies, 2000–2016
    Sevillano, M.C.; Jareño, J.
  • Accounting recognition and the relevance of earnings as an explanatory variable for returns
    Wardfield, T.; Wild, J.
  • A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring
    Xia, Y.; Liu, C.; Li, Y.Y.; Liu, N.
  • Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction
    Zieba, M.; Tomczak, S.K.; Tomczak, J.M.
  • Interpretable machine learning
    Molnar, C.