Posted: May 14, 2020
This research presents a novel computational framework that integrates environmental accounting metrics with machine learning algorithms to predict corporate sustainability performance and its impact on long-term shareholder value creation. Unlike traditional approaches that treat environmental accounting as a compliance exercise, our methodology employs a multi-modal data fusion technique inspired by recent advances in healthcare diagnostics, specifically adapting principles from multimodal deep learning systems used in autism detection. We developed a proprietary Environmental Performance Index (EPI) that synthesizes data from carbon emissions tracking, water usage metrics, waste management statistics, and supply chain sustainability indicators. Our computational model processes these diverse environmental datasets alongside traditional financial metrics to identify patterns and correlations that conventional analysis methods typically overlook. The research demonstrates that companies with superior environmental accounting practices exhibit 27
Downloads: 87
Abstract Views: 547
Rank: 358868