Nutri-Ai

Inspiration I was inspired to build this project when I needed a diet plan but found that dieticians were costly and existing solutions suggested food items unavailable in my region. This led me to create a custom AI-powered diet recommendation system that provides personalized meal plans based on user data and local availability. What it does Our AI-powered diet planner takes the guesswork out of nutrition by recommending customized meal plans based on your height, weight, age, and region. Key Features: Personalized Nutrition – Plans tailored to your body metrics and goals (weight gain, loss, or maintenance).location-Based Recommendations – Get diet plans aligned with local cuisine and available ingredients.AI-Driven Precision – Backed by advanced machine learning to ensure optimal health outcomes.Seamless Experience – Simple registration, instant recommendations, and easy tracking.Start eating smarter today with our science-backed, AI-driven diet planner How we built it Backend Development – Built using Spring Boot, connected to a local MongoDB database to store user data and generated diet plans. 2️⃣ AI Model for Diet Prediction – Trained using a self-made dataset with the following libraries: Python Libraries Used: pandas, numpy, matplotlib, seaborn sklearn (for model training and evaluation) xgboost, randomforestclassifier (for predictive modeling) joblib (for saving trained models) Flask, pickle, os (for serving AI predictions via API) Challenges we ran into Selecting the Right ML Model – Experimented with multiple classifiers before finalizing XGBoost. 🔹 Dataset Creation – No public dataset fit our needs, so we built a custom dataset. 🔹 Integration Issues – Connecting the AI model with our Spring Boot backend required careful API design and debugging. What we learned Throughout this project, I gained hands-on experience in: Spring Boot for backend development MongoDB for data storage Machine learning techniques for predictive modeling API integration between AI and backend What's next for Nutri-Ai Backend: Deploy your Spring Boot app on AWS (EC2), Heroku, or Render. Database: Use a cloud-based MongoDB Atlas instead of a local database. AI Model: Deploy the Flask API on AWS Lambda, Google Cloud, or Render for better scalability. 2️⃣ Improve AI Model 🤖 Collect real user data to fine-tune the model. Experiment with deep learning (LSTMs or CNNs) for better predictions. Optimize performance with feature engineering & hyperparameter tuning. 3️⃣ Enhance the Frontend 🎨 Convert your HTML/CSS/JS frontend into a React or Vue.js application. Add a dark mode & UI improvements for a better user experience. Implement a progress tracker so users can log their weight changes. 4️⃣ Add More Features 🚀 Chat with Dieticians – Let users consult nutritionists through a chat feature. Recipe Suggestions – Generate meal recipes based on AI recommendations. Calorie & Macro Tracker – Help users track their daily intake. 5️⃣ Monetization 💰 Introduce a freemium model (basic diet plans for free, premium ones with expert consultation). Create a mobile app for better accessibility.