Vol. 2, Issue 2, Part A (2025)

The growing demand for rapid, accurate, and non-destructive assessment of nutritional quality in traditional foods has accelerated the application of machine learning (ML) in food composition analysis. Date palm (Phoenix dactylifera L.) present juice and gur nutrient-rich sweeteners consumed widely in South Asia and the Middle East show substantial variability in nutrient composition due to cultivar differences, seasonal variations, extraction techniques, and processing conditions. Conventional laboratory analyses are time-consuming, expensive, and require skilled personnel, highlighting the need for predictive computational models capable of estimating nutrient profiles efficiently. The present research applies supervised machine learning algorithms to model and predict the nutrient composition of date palm present juice and gur, incorporating parameters such as moisture, sucrose, reducing sugars, proteins, minerals, and caloric content. Using historical experimental datasets (pre-2024) collected from previously published research, seven ML techniques Random Forest, Support Vector Regression, Gradient Boosting, k-Nearest Neighbours, Artificial Neural Networks, Ridge Regression, and Decision Trees were trained and evaluated based on RMSE, MAE, and R² scores. The Random Forest and Gradient Boosting models demonstrated the highest predictive accuracy for most nutrient attributes, indicating their suitability for complex non-linear relationships inherent to biological data. Additionally, feature importance analysis revealed sucrose and moisture as the most influential predictors across models. The results confirm that ML-based predictive modelling can serve as a robust alternative to conventional chemical analysis, enabling faster decision-making in food quality monitoring, processing optimization, and value-chain enhancement for date palm derivatives. This approach also facilitates improved traceability and standardization in artisanal gur production systems. Overall, the research contributes toward modernizing traditional food industries by integrating AI-driven tools into nutrient evaluation frameworks.