Fertilizer recommendation plays a vital role in improving agricultural productivity and ensuring sustainable farming practices. This study applies machine learning models, including Logistic Regression, Decision Tree, Naive Bayes, and Support Vector Machine (SVM), to recommend suitable fertilizers based on key parameters such as soil nutrients (Nitrogen, Phosphorus, Potassium), soil moisture, temperature, and humidity. After data preprocessing and feature selection, model performance is evaluated using accuracy-based metrics to identify the most effective prediction model. Results indicate that machine learning approaches provide more accurate and consistent fertilizer recommendations compared to traditional methods. The system integrates real-time environmental data and provides water level suggestions and fertilizer price estimation to support cost-effective decision-making. This research demonstrates the effectiveness of machine learning in precision agriculture and suggests future enhancements through advanced models and expanded real-time data integration. Agriculture is a fundamental sector that supports food production, economic stability, and sustainable development. One of the most critical factors influencing crop productivity is the appropriate use of fertilizers. Selecting the correct fertilizer based on soil composition and environmental conditions is essential for improving crop yield, maintaining soil health, and reducing unnecessary agricultural expenses. However, farmers often rely on traditional knowledge or generalized recommendations, which may not accurately reflect real-time soil and climate conditions. With the advancement of machine learning and web technologies, intelligent decision-support systems can be developed to provide precise, data-driven agricultural recommendations. This project presents a Fertilizer Recommendation System designed to assist farmers and agricultural practitioners in selecting the most suitable fertilizer based on soil nutrient values such as Nitrogen (N), Phosphorus (P), and Potassium (K), along with environmental parameters including temperature, humidity, and moisture. The system integrates machine learning models with a web-based interface to provide accurate and practical recommendations. The system enhances decision-making by automatically fetching environmental parameters such as temperature and humidity through API integration, ensuring real-time and location-relevant inputs. Based on the analyzed data, the system not only recommends the appropriate fertilizer but also suggests the required water level for crops according to weather and soil conditions. Additionally, it provides an estimated price of the recommended fertilizer, helping users make economically informed decisions. The project is implemented using Python and Flask to create a web-based application where users can input soil and crop details through an interactive interface. Machine learning models trained on agricultural datasets are stored using serialization techniques and deployed within the system to generate predictions efficiently. The system processes user inputs, applies the trained model, and returns fertilizer recommendations along with supporting agricultural insight.