Beyond predicting overall volumes, the work extends to sub-categories, including ward allocation and patient complexity, providing more granular insights for hospital resource planning.

I experimented with a range of models, including SARIMAX for time-series forecasting, LSTM for sequence learning, and Random Forest for robust feature-driven predictions. Throughout the project, I gained hands-on experience in feature engineering, data cleaning and pre-processing, training and testing algorithms, alongside comparing algorithm performance to determine the most suitable approaches for different forecasting objectives.

Note: the project is contained in a private repository as it contains sensitive data.

The application was designed to let users record runs, wickets, overs, and other match statistics in real time, with a clean and intuitive interface tailored for mobile use.

This project not only improved my proficiency in Swift and Xcode, but also gave me practical experience in UI/UX design, data persistence, and application testing. It highlighted the end-to-end development process, from planning and design to implementation and debugging.

View on GitHub

The app allowed users to record runs, wickets, overs, and other match details, while maintaining a consistent and responsive interface across both iOS and Android devices.

This project gave me practical experience in Dart programming, Flutter widgets, and responsive UI design. I also explored best practices for building layouts that adapt seamlessly to different screen sizes and platforms, strengthening my understanding of cross-platform mobile development.

View on GitHub

By collecting real-world football data and applying predictive models, I gained hands-on experience in data-driven sports analytics.

Key aspects of the project includes web scraping, data analysis, machine learning, alongside combined data collection, analysis, and predictive modeling to gain practical experience in real-world football analytics.

This project strengthened my skills in Python programming, data wrangling, feature engineering, and model evaluation, while giving me a deeper understanding of how sports analytics and machine learning can be applied to predict outcomes.

View on GitHub

The key features of AUnity include built-in language selection, an AI chatbot, and trusted information sources to make knowledge simple and accessible for everyone.

For this project, I contributed primarily to the frontend development, creating a clean, user-friendly interface that encourages exploration and engagement with the platform.

AUnity demonstrates my skills in HTML, CSS, JavaScript, and responsive web design, while showing my ability to design inclusive digital experiences that serve diverse communities.

Check out our demo video on YouTube