ABSTRACT
PurposeThe 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.