Predictive model on employee stock ownership impacting corporate performance

Area of Science:

• Management Science
• Artificial Intelligence in Business
• Financial Accounting

Background:

• Smart manufacturing enterprises face challenges in human capital strategies and incentive mechanisms.
• The dynamic impact of Employee Stock Ownership Plans (ESOPs) on corporate performance in smart manufacturing remains unclear.
• Existing research lacks comprehensive models to predict long-term ESOP effectiveness within intelligent manufacturing contexts.

Purpose of the Study:

• To develop and validate an AI-driven prediction model for assessing the dynamic impact of ESOPs on enterprise performance.
• To analyze the long-term, dynamic, and nonlinear effects of ESOPs, considering smart manufacturing maturity and social sentiment.
• To utilize Explainable AI (XAI) for interpreting ESOP effectiveness and providing decision support for management accounting.

Main Methods:

• Integration of Artificial Intelligence (AI) with accounting principles.
• Development of a prediction model combining language modeling and social sentiment mass data analysis.
• Application of Long Short-Term Memory (LSTM) networks and SHAP value methods for explainable AI (XAI) analysis.

Main Results:

• A novel prediction model integrating financial, social sentiment, and operational data with AI (LSTM, LLM) was constructed.
• Explainable AI (XAI) successfully elucidated the long-term, nonlinear impact of ESOPs, smart manufacturing maturity, and social sentiment.
• The study provides a framework for attribution analysis of ESOP incentive effects, enhancing management accounting decision support.

Conclusions:

• ESOPs play a crucial role in the intelligent transformation of manufacturing enterprises, influencing performance dynamically.
• The developed AI and XAI framework offers new predictive tools and theories for evaluating ESOP effectiveness.
• This research provides empirical data and decision support for optimizing ESOP design and implementation in smart manufacturing.