Modern evolvements of the technologies have been leading to a profound influence on the financial market. The introduction of constituents like Exchange-Traded Funds, and the wide-use of advanced technologies such as algorithmic trading, results in a boom of the data which provides more opportunities to reveal deeper insights. However, traditional statistical methods always suffer from the high-dimensional, high-correlation, and time-varying instinct of the financial data. In this dissertation, we focus on developing techniques to stress these difficulties. With the proposed methodologies, we can have more interpretable models, clearer explanations, and better predictions.

The paper proposes a new asset pricing model - the News Embedding UMAP Selection (NEUS) model, to explain and predict the stock returns based on the financial news. The proposed model is built on top of the recent achievements in asset pricing and natural language processing. From the asset pricing perspective, the NEUS model is based on the Adaptive Multi-Factor (AMF) model proposed by Zhu et al. [2020], which provides a modern and more general framework for multi-factor models. The AMF model contains the traditional well-known Fama-French 5-factor model (FF5) Fama and French [2015] as a special case. The finance theory behind the AMF model is the Generalized Arbitrage Pricing Theory (GAPT) proposed in Jarrow and Protter [2016] and Jarrow [2016] as a modern and more general framework of the traditional Arbitrage Pricing Theory (APT) proposed by Ross [1976].

The purpose of this paper is to test the multi-factor beta model implied by the generalized arbitrage pricing theory (APT) and the Adaptive Multi-Factor (AMF) model with the Groupwise Interpretable Basis Selection (GIBS) algorithm, without imposing the exogenous assumption of constant betas. The intercept (arbitrage) tests validate both the AMF and the Fama-French 5-factor (FF5) model. We do the time-invariance tests for the betas for both the AMF model and the FF5 in various time periods. We show that for nearly all time periods with length less than 6 years, the beta coefficients are time-invariant for the AMF model, but not the FF5 model. The beta coefficients are time-varying for both AMF and FF5 models for longer time periods. Therefore, using the dynamic AMF model with a decent rolling window (such as 5 years) is more powerful and stable than the FF5 model.