A Literature Review on the Model of EGARCH-MIDAS, LMM, GBM for Stock Market Prediction

The stock market prediction has been an active research area in finance and eco-nomics for decades. In recent years, mathematical models have often been used by various experts and scholars for stock market forecasting because of their ability to take into account complex relationships and patterns in the data. This paper summarizes several common mathematical models for stock market prediction, including the Exponential Generalized Autoregressive Conditional Heteroskedasticity - Mixed Data Sampling Model (EGARCH-MIDAS), The Local Linearization Method Model (LMM), and The Geometric Brownian Motion Model (GBM). This paper will discuss the theoretical basis, modeling methods, ad-vantages, and limitations of each model, as well as their application scope and evaluation analysis.