All Projects

•

A production-ready social experience platform for local hangouts and group journeys with real users.

•

Mobile app: iOS & Android (React Native, Expo 52) with multi-provider auth, Google Maps-based discovery, push notifications, QR check-in, payments, ratings.

•

Backend: Node.js/Express TypeScript API on GCP with MongoDB, Firebase, geospatial queries, role-based access (Users, Hosts, Captains).

•

Payments: Multi-gateway integration (Razorpay, PayU, Cashfree) with UPI/cards.

•

Security & Quality: JWT auth, validation, rate limiting; TypeScript, ESLint, Prettier, Jest.

•

Developed an engaging website for a dance class, using Django, ReactJS, SQLite and JWT for session management

•

Streamlined the dance class's online presence, effectively showcasing their expertise, and facilitating the sale of online classes and workshops, enhancing their reach and impact

•

Developed a user-friendly interface allowing easy signups and membership application

•

Built a comprehensive ticketing application using Django-REST, React.js, PostgreSQL and JWT for session management

•

Applied Redux for effective state management in project development

•

Created a user-friendly interface for effortless event creation and ticket booking

•

Developed a multi-service application integrating Django for authentication and Flask for note-taking functionality

•

Authentication Service: Implemented using Django to manage user authentication and registration, operational on port 5050

•

Note Taking Service: Utilized Flask to enable CRUD operations for notes, accessible via port 5030

•

Database Connectivity: Established a PostgreSQL database with persistent volumes, facilitating data storage for both services

•

Docker Compose Implementation: Employed Docker Compose for containerizing and orchestrating services, ensuring easy deployment and management

•

Developed a deep learning system using VGG16 and VGG19 models to classify diseases in potato plants based on leaf conditions

•

Collected and pre-processed diverse datasets of potato plant images, ensuring data quality for effective model training

•

Implemented data augmentation techniques to expand the dataset, enhancing the model's robustness and accuracy

•

Achieved an average accuracy of 91% in classifying four types of potato plant diseases, addressing the decline in harvest quality and quantity caused by diseases

•

Created a Machine Learning Pipeline to predict house SalePrice, encompassing phases like Data Analysis, Feature Engineering, Exploratory Data Analysis, Model Building, and Model Deployment in line with the standard Data Science project life cycle.

•

Utilized a Kaggle dataset focused on Bengaluru house prices to drive the predictive analysis.

•

Performed comprehensive analysis, feature engineering, and exploratory data analysis, documented within the .ipynb file.

•

Utilized essential packages including numpy, pandas, matplotlib, seaborn, and sklearn for data manipulation, visualization, and model development.

•

Performed Data Cleaning, Data Analysis, and Data Preprocessing on telecommunication company data to prepare it for predictive modeling.

•

Explored and trained various machine learning models, including Logistic Regression, SVM, Random Forest, Naive Bayes and Decision Tree

•

Achieved a commendable 80% accuracy rate with Logistic Regression after hyper parameter tuning, demonstrating the predictive model's effectiveness in forecasting customer churn in the telecommunication sector.