A Machine Learning-Based Framework for Agile Product Development and Growth Strategy Optimization
Main Article Content
Abstract
Agile product development has become a dominant approach for managing complexity and uncertainty in modern, data-intensive product ecosystems; however, its effectiveness is often constrained by limited use of predictive and prescriptive analytics in decision-making. This study proposes a machine learning–based framework that integrates agile development processes with growth strategy optimization by leveraging multi-dimensional data from product execution, user behavior, and market dynamics. The framework employs supervised and ensemble learning models for predicting key product and growth outcomes, alongside optimization techniques to support feature prioritization, resource allocation, and strategic planning within agile constraints. Empirical results demonstrate that the proposed approach significantly improves predictive accuracy, enhances delivery efficiency, and strengthens alignment between sprint-level execution and long-term growth objectives. Longitudinal validation across multiple sprint cycles reveals that continuous learning and feedback loops further increase model reliability and strategic coherence over time. The findings highlight the potential of machine learning to transform agile product development into a data-driven, adaptive system that balances operational agility with sustainable growth.