Financial Performance Evaluation is the process of assessing a company’s financial health, profitability, and growth potential using key financial indicators and metrics. The study proposes a data-driven framework for the integrated evaluation of enterprise financial performance by considering both financial and non-financial recoveries, known as Environmental, Social, and Governance (ESG). The study utilizes a dataset comprising 11,000 records from 1,000 firms, providing a robust foundation for the analysis of financial and ESG factors. Financial analysis in a traditional manner may prove inadequate in balancing the complexities of the new business environment and the ever-shifting financial data. The framework deploys Deep-Convolutional Neural Networks (DCNNs) for the prediction of future sustainability and financial scenarios. The framework uses ESG criteria along with financial parameters, thereby stretching its applications beyond short-term profit maximization for long-term viability and sustainable growth. It qualifies itself as an appropriate candidate to handle complex datasets, but also provides insightful outputs to help strategic planners in decisions ensuring both financial development and development in a responsible manner. The study stresses the impact of ESG on financial performance and shows that companies with strong sustainability aspects maintain healthy financial growth in recent years. The model achieved strong predictive accuracy, with a Mean Absolute Error (MAE) of 0.0189, Mean Squared Error (MSE) of 0.0007, and a Root Mean Squared Error (RMSE) of 0.0265, indicating highly reliable and precise forecasting capabilities. Hence, the DCNN architecture outperforms others in predicting the future of financial and sustainability metrics, thereby proving the potential of Deep Learning (DL) for evaluating financial performance.
Yi Xu (Sun,) studied this question.