Stock market price prediction model based on grey prediction and ARIMA

Abstract

Nowadays more and more people like to invest in volatile assets, and it is the goal of every market trader to maximize the total return by developing a reasonable investment strategy. We first predicted the daily value of gold and bitcoin for five years based on known data, we built two models, one is Improved Metabolic Gray Model (Abbreviated as IGM), the other is Time Series Model ARIMA. The application of the model helps investors make investment decisions and improve economic returns.

Analysis of the Relationship Between Cross Capital Flows and Stock Exchange Index with Machine Learning

“…In addressing the FDI-stock market dilemma, this research also aligns with In terms of implications for investor decision-making, this study echoes Yang's (2023) ambition to use AI for enhanced stock price forecasting, extending its utility to the macroeconomic sphere. By identifying key drivers of the BIST 100 index, the study enriches the empirical discourse, aiding investment strategies in line with the practical applications suggested by Beck et al, (2023) in managing capital flows.…”

“…The interplay between FDI and stock market indices has been scrutinized using various econometric models (Lee et al, 2022;Xiu, 2022;Yang, 2023). However, these investigations typically depend on conventional statistical methods, which may not sufficiently address non-linear and intricate relationships.…”

“…Feature engineering is acknowledged as a fundamental component in augmenting ML model performance (Yang, 2023). This study capitalizes on feature engineering techniques specifically designed for the BIST100 index dataset, thus enhancing the predictive accuracy of the ML model.…”

“…Prior research has highlighted the significant impact of FDI on stock market performance and broader economic health. However, traditional econometric models frequently fail to address the non-linear and intricate relationships in these dynamics (Lee et al, 2022;Xiu, 2022;Yang, 2023). This study's innovative use of OMP, renowned for its effectiveness in feature selection, addresses these shortcomings and fills a critical gap in the current body of literature.…”