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

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with International Journal for Applied Information Management agree to the following terms: Authors retain copyright and grant the International Journal for Applied Information Management right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share (copy and redistribute the material in any medium or format) and adapt (remix, transform, and build upon the material) the work for any purpose, even commercially with an acknowledgement of the work's authorship and initial publication in International Journal for Applied Information Management. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in International Journal for Applied Information Management. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).