Against the backdrop of escalating global carbon emission reduction urgency and China’s "dual carbon" goals, individual carbon trading (ICT) has emerged as a key measure to tap into consumer-side emission reduction potential. However, the current ICT mechanism remains in the exploratory stage, plagued by limited access to formal trading channels, strict entry barriers, and low public penetration, only 5 carbon exchanges in China allow individual participation, with fewer than 10,000 total participants. Focusing on mechanism integrity and integrating the carbon inclusive system, this study explores the influencing factors of ICT operation and constructs targeted optimization strategies. Based on Mechanism Design Theory, the Theory of Planned Behavior, and Value-Belief-Norm Theory, a theoretical model covering five core ICT components was established. Using data from 1,200 questionnaires across 15 Chinese cities, multiple linear regression and hierarchical regression were employed to analyze the impacts of institutional fairness, technical usability, social atmosphere, and individual cognition. Results show: (1) Institutional fairness increases quota compliance by 38% through transparent rules; (2) User-friendly technical tools boost engagement by 1.8x, enhancing accounting accuracy and platform efficiency; (3) Social atmosphere moderates the effect of individual cognition on incentive conversion, particularly strongly in rural areas; (4) Individual cognition mediates the relationship between social atmosphere and trading platform efficiency. Additionally, optimizing mechanism components is more critical for long-term operation than single incentives. This study proposes a multi-dimensional optimization framework, providing theoretical and policy references for improving ICT integrity and advancing "dual carbon" goals.

This paper proposes a new forecasting framework for the stock market that combines machine learning algorithms with several technical analyses. The paper considers three different algorithms: the Random Forests (RF), the Gradient-boosted Trees (GBT), and the Deep Neural Networks (DNN), and performs forecasting tasks and statistical arbitrage strategies. The portfolio weight optimization strategy is also proposed to capture the model's return and risk information from output probabilities. The paper then uses the stock data in the Chinese A-share market from January 1, 2011, to December 31, 2020, and observes that all three machine learning models achieve significant returns in the Chinese stock market. The DNN achieves an average daily return of 0.78% before transaction costs, outperforming the 0.58% of the RF and 0.48% of the GBT, far exceeding the general market level. The performance of the weighted portfolio based on the ESG score is also improved in all three machine learning strategies compared to the equally weighted portfolio. These results help bridge the gap between academic research and professional investments and offer practical implications for financial asset pricing modelling and corporate investment decisions.