Applying Artificial Intelligence and Big Data Analysis in Predicting the Effectiveness of Strategic Decision-Making in the Green Hotel Standards

Abstract

Trinh Quang Minh and Ngo Thi Lan

This research proposes an Integrated AI-Driven Predictive Decision Intelligence Framework to evaluate and forecast the long-term effectiveness, ROI, and operational risk of strategic decisions in the hospitality industry. Facing market volatility, high staff turnover, operational risks, and multi-dimensional compliance requirements—such as the 11 ASEAN Green Hotel Standards and department-specific Occupational Health and Safety (OHS) mandates—hotel executives in Southeast Asia often rely on historical financial disclosures, reactive intuition, and fragmented data silos. Grounded in the synthesis of Information Processing Theory (IPT) and the Dynamic Capabilities View (DCV), the study establishes a quantitative, data-driven framework that bridges data science methods with executive strategic planning. The framework integrates internal corporate big data (financial metrics, annual reports, energy/water utility logs, OHS incident records) with external market signals (unstructured online guest review sentiment) via automated Python parsing pipelines (PyMuPDF, Pandas) and Natural Language Processing (NLP). Supervised machine learning algorithms (Random Forest, XGBoost, Neural Networks) combined with Partial Least Squares Structural Equation Modeling (PLS-SEM) process these multi-source inputs to forecast key performance indicators, including Revenue Per Available Room (RevPAR), Customer Satisfaction Index (CSI), and Operational Risk Scores. By enabling pre-investment scenario simulations, this research empowers hotel executives to overcome bounded rationality, optimize sustainability and OHS compliance costs, and achieve a sustained competitive advantage.

PDF