New Evidence to Assess the Asset Pricing Model: An Empirical Investigation Based on Bayesian Network

An extensive, in-depth study of risk factors seems to be of crucial importance in the research of the financial market in order to prevent (or reduce) the chance of developing this return. It represents market anomalies. This study confirms that the q-factors model is better than the other traditional asset pricing models in explaining individual stock return in the US over the 2000–2017 period. The main focus of data analysis is, on the use of models, to discover and understand the relationships between different factors of risk market anomaly. Recently, Fama and French presented a five-factor model that captures the size, value, profitability, and investment patterns in average stock market returns better than their three-factor model presented previously in 1993. This paper explores a shred of new empirical evidence to assess the asset pricing model through an extension of Fama and French model and a report on applying Bayesian Network (BN) modeling to discover the relationships across different risk factor. Furthermore, the induced BN was used to make inference taking into account sensibility and the application of BN tools has led to the discovery of several direct and indirect relationships between different parameters. For this reason, we introduce additional factors that are related to behavioral finance such as investor’s sentiment to describe a behavior return, confidence index, and herding. It is worth noting that there is an interaction between these various factors, which implies that it is interesting to incorporate them into the model to give more effectiveness to the performance of the stock market return. Moreover, the implemented BN was used to make inferences, i.e., to predict new scenarios when different information was introduced.