Human–AI Collaborative Decision Intelligence for Context-Aware Corporate Planning Through Integrated Knowledge Retrieval and Predictive Reasoning

Main Article Content

Dwi Sugianto
Adi Setiawan
Wiwin Sulistyo

Abstract

Corporate planning increasingly requires decision support mechanisms that can connect distributed organizational knowledge, dynamic business context, and predictive assessment into coherent planning recommendations. This study proposes a context-aware decision intelligence framework that integrates semantic knowledge retrieval, contextual representation, predictive reasoning, and risk-adjusted recommendation ranking for corporate planning. The framework was evaluated across five planning domains, namely finance, operations, risk management, market planning, and executive policy. The integrated retrieval model outperformed keyword-based and semantic-only baselines, achieving the highest precision in executive policy documents at 0.94 and the highest recall in the same domain at 0.91. Across all domains, integrated precision ranged from 0.86 to 0.94, while integrated recall ranged from 0.83 to 0.91. Predictive reasoning also produced stable scenario assessment results across five planning scenarios, with accuracy values between 0.84 and 0.91 and F1-scores between 0.81 and 0.89. Balanced growth achieved the strongest predictive result, with 0.91 accuracy, 0.90 precision, 0.88 recall, and 0.89 F1-score. Recommendation evaluation showed that the proposed framework achieved 0.91 NDCG@3, 0.93 NDCG@5, 0.89 hit rate, and 0.88 mean reciprocal rank, outperforming retrieval-only, prediction-only, and non-contextual ranking baselines. Context sensitivity analysis further showed that recommendation priorities changed appropriately across business conditions, with risk mitigation scoring 0.91 under high-risk conditions, capacity allocation scoring 0.90 under capacity limitation, and cost efficiency scoring 0.89 under budget constraint. Interpretability assessment confirmed the managerial usefulness of the framework, with expert scores of 4.6 for evidence clarity, 4.4 for prediction explanation, 4.1 for risk transparency, 4.5 for actionability, and 4.7 for context traceability. These findings indicate that corporate planning recommendations become more accurate, adaptive, and explainable when retrieval relevance, predictive feasibility, contextual fit, and risk exposure are evaluated jointly.

Article Details

How to Cite
[1]
D. Sugianto, A. Setiawan, and W. Sulistyo, “Human–AI Collaborative Decision Intelligence for Context-Aware Corporate Planning Through Integrated Knowledge Retrieval and Predictive Reasoning”, Int. J. Appl. Inf. Manag., vol. 6, no. 4, pp. 507–524, Nov. 2026.
Section
Articles