In this research, the analysis and forecasting of corporate value are conducted using financial data, ESG (Environmental, Social, and Governance) indicators, and climate risk variables. The main objective of this study is to develop a more precise predictive model through advanced machine learning algorithms such as XGBoost and multilayer neural networks (MLP), in order to examine the impact of ESG data and climate risks on corporate valuation.

The results indicate that ROE (Return on Equity) has the greatest influence on predicting firm value, whereas non-financial factors such as ESG scores and climate risks exhibit relatively smaller effects. The MLP model outperformed XGBoost in prediction accuracy and provided higher precision in data simulation.

This study also revealed that, although climate risks and ESG indicators have a lesser impact on short-term financial forecasts, they should be integrated into financial analyses as essential tools for evaluating the long-term sustainability of firms. Based on these findings, it is recommended that more sophisticated and accurate models be employed for forecasting corporate value and assessing the effects of climate risk within capital markets.