Based on machine learning methods, this paper systematically studies the cross-sectional excess returns of A-share stocks. Taking 5,648 stocks in China's A-share market from 2020 to 2024 as a sample, a multi-dimensional factor system covering fundamentals and macro variables was constructed, and the out-of-sample performance of multiple models was compared under the rolling forecast framework of Expanding Window. The empirical results show that the nonlinear machine learning model continues to obtain positive information coefficients in most quarters, and its prediction signals can be converted into stable long-short portfolio returns, while the prediction ability and investment performance of traditional linear models decay significantly with time. In terms of risk control, LightGBM shows a relatively better trade-off between return level and drawdown magnitude. The research in this paper confirms that the machine learning method that combines a nonlinear structure and cross-sectional heterogeneity can effectively improve the return prediction ability and investment performance of the A-share market and provides practical empirical evidence for quantitative stock selection.

Show more

Stock return prediction is a fundamental but difficult issue in financial research because of the noise and dynamics of market data. Although recent research has improved the ability of existing machine learning model prediction, these methods are difficult to interpret and lack practical application value due to their "black box" nature. This paper constructs an explainable machine learning framework to achieve high-accuracy predictions of short-term stock excess returns and strive for greater interpretability in economics; Compared with other complex models. Taking the daily trading data of Apple Inc. (AAPL) as a single-stock example, this paper constructs a set of economically meaningful features based on historical returns, volatility and trading volume. A linear regression model is used as the central prediction tool, and interpretability can be built into this specific form of a linear model. Out-of-sample forecasts use the rolling window method, and prediction performance is compared with a naive historical mean benchmark. Based on experiments, the current basis of explanation using an explainable linear model has been shown to be relatively stable in baseline prediction. According to the coefficient analysis, in addition to conforming to some basic Finance theory patterns. A return pattern that exists for one day appears. A Volatility-Return relationship also holds currently. This paper shows that interpretive models, in combination with carefully selected features, achieve satisfactory prediction performance; at the same time, it is also found through the analysis of economic implications that such an approach helps explore the essence of changes in stock returns.

Show more

China faces a severe issue of abandoned farmland, affecting 107 counties across 21 provinces and municipalities. In Sichuan Province, for example, the abandoned land rate in contracted farmland reached 2.2% in 2022, ranking among the highest nationwide and directly threatening food security. Using Huangtan Village in Pingchang County as a case study, field research conducted among 10 farming households revealed that all surveyed farmers were unwilling to farm, with 7 expressing willingness to sell their land. Analysis identified four core reasons for low farming motivation: (1) meager farming income (including subsidies) barely covering costs, significantly lower than migrant workers' earnings; (2) fragmented farmland, lack of field roads, and inadequate irrigation facilities hindering large-scale cultivation and agricultural machinery operations; (3) low agricultural subsidy standards and policies lacking long-term transparency, with some regions experiencing discontinuous agricultural planning due to leadership changes; and (4) aging rural labor forces struggling to sustain high-intensity farming. To address this, targeted countermeasures are proposed: improving agricultural economic efficiency, optimizing grain procurement and subsidy mechanisms, strengthening agricultural infrastructure, stabilizing agricultural policies, and promoting land circulation and agricultural technology dissemination to boost farmers' enthusiasm for farming and alleviate abandoned farmland issues.

Show more

This study systematically examines the urban governance model emerging from the development of the Guangdong-Hong Kong-Macao Greater Bay Area (GBA) and its driving mechanisms for regional coordinated development. As a strategic initiative under the "one country, two systems" framework, the GBA has cultivated a distinctive governance system while advancing multi‑dimensional coordination across economic, social, spatial, and ecological domains. Using a qualitative case‑study approach, this research draws on a systematic literature review, policy text analysis, and a comparative study to analyze the model's core components, operational logic, and practical outcomes. Findings reveal that the GBA has established a composite governance model characterized by "multi‑level strategic coordination, networked multi‑actor co‑governance, incremental rule and policy alignment, and digitally enabled smart governance." The mechanism mode can be summarized as: dynamic collaboration in the constantly adjusted common planning, policy pilot and innovation, interest bargaining and balancing. All these provide effective support for industrial upgrading of the region ,spatial optimization,social integration as well as ecological co-management .Meanwhile constraints are found to exist lagging behind soft connectivity due institutional differences at network structure imbalance inside governance network between different levels&sectors ,imperfect interest coordination mechanism unsustainable in long run. These factors currently hinder deeper regional integration.

Show more