Boosting of fruit choices using machine learning-based pomological recommendation system

Abstract Pomology, also known as fruticulture, is a significant contributor to the economies of many nations worldwide. While vertical farming methods are not well-suited for fruit cultivation, substrate-based cultivation commonly practiced. Vertical use no soil plants, and done in vertically stacked layers. Therefore, smaller herbs best suited such whereas, majority trees big woody. well trees. However, maximize production, smarter substrate needed. Utilizing remote sensing techniques, Internet Things (IoT) devices, agriculture sensors, cloud computing, allows precision smart autonomous systems. Nevertheless, lack understanding nutrient requirements, growing conditions, health conditions can result reduced production. To address these challenges, this paper proposes an intelligent model based on machine learning that recommends grow prevailing climatic conditions. The system trained dataset includes details eleven different fruits, Nitrogen (N), Phosphorous (P), Potassium (K), temperature, humidity, pH, rainfall. takes into account type contents recommend most suitable climate. enhance model's efficiency, two novel Gradient-based Side Sampling (GOSS) Exclusive Feature Bundling (EFB), have been incorporated. results show proposed has achieved 99% accuracy recommending right given environmental As result, potential significantly improve profitability pomology industry boost national economies.