Stocks are the most common financial investment products and attract many investors around the world. However, stock price volatility is usually uncontrollable and unpredictable for the individual investor. This research aims to apply different machine learning models to capture the stock price trends from the perspective of individual investors. We consider six traditional machine learning models for prediction: decision tree, support vector machine, bootstrap aggregating, random forest, adaptive boosting, and categorical boosting. Moreover, we propose a framework that uses regression models to obtain predicted values of different moving average changes and converts them into classification problems to generate final predictive results. With this method, we achieve the best average accuracy of 0.9031 from the 20-day change of moving average based on the support vector machine model. Furthermore, we conduct simulation trading experiments to evaluate the performance of this predictive framework and obtain the highest average annualized rate of return of 29.57%.
Intertemporal decision-making, which involves making choices between outcomes at different time points, is a fundamental aspect of human behavior. Understanding the underlying mental processes is vital for comprehending the complexities of human decision-making and choice behavior.
The main objective of this study is to investigate the interplay of mental processes, specifically cognitive evaluation, subjective valuation, and comparison, in the context of intertemporal decision-making, with a specific focus on understanding the discounting process.
Development of a mathematical representation of the discounting process that incorporates the mental processes associated with intertemporal decision-making.
Our findings indicate that hyperbolic discounting aligns well with the cognitive processes underlying intertemporal decision-making. Subsequent research will employ qualitative questionnaires to establish the discount function relevant to specific groups, thereby enhancing our comprehension of the discounting process within intertemporal decision-making.
Assuming that stock prices follow a multi-fractional Brownian motion, we estimated a time-varying Hurst exponent ($ h_t $). The Hurst value can be considered a relative volatility measure and has been recently used to estimate market inefficiency. Therefore, the Hurst exponent offers a level of comparison between theoretical and empirical market efficiency. Starting from this point of view, we adopted a multivariate conditional heteroskedastic approach for modeling inefficiency dynamics in various financial markets during the 2007 financial crisis, the COVID-19 pandemic and the Russo-Ukranian war. To empirically validate the analysis, we compared different stock markets in terms of conditional and unconditional correlations of dynamic inefficiency and investigated the predicted power of inefficiency measures through the Granger causality test.
This study analyzes the impact of global financial integration and monetary policies from the United States, European Union and Japan on China's financial markets post-pandemic. Using TVP-FAVAR (Time-Varying Parameter Factor Augmented Vector Autoregression) and TVP-VAR-DY (Time-Varying Parameter Vector Autoregression DY) models, a Chinese financial market stress index was developed, showing that developed nations' monetary policies influence China's financial stress. The impact varies based on the economy's size and policy effectiveness. The spillovers occur mainly through accelerated short-term capital flows and foreign exchange reserve fluctuations. These effects have evolved over two decades, particularly noticeable during economic crises and the COVID-19 pandemic, highlighting the need for emerging economies, like China, to protect against international financial spillovers.