Featured Projects
Planno
Description
Planno is a scheduling platform that helps bishops of the Church of Jesus Christ of Latter-Day Saints create booking links for interviews and meetings, enabling members to schedule directly from the bishop's availability.
Problem
Coordination of meetings between bishops and members requires extensive back-and-forth communication, leading to scheduling conflicts, missed appointments, and significant time spent on manual coordination.
Solution
Planno provides shareable booking links that display real-time availability, allowing members to self-schedule appointments. The platform integrates with Google Calendar for automatic sync and supports Apple Calendar downloads, ensuring seamless scheduling across all devices while keeping meetings organized and reducing coordination overhead.
Tech Stack
TastyFood
Description
TastyFood is a custom food ordering platform that enables local restaurants to accept online orders directly from customers, providing a complete ordering and delivery management system.
Problem
Local restaurants lose 15-30% of each order's revenue to third-party delivery services like DoorDash and UberEats. They also lose direct customer relationships, control over pricing, and the ability to manage promotions effectively.
Solution
By owning their ordering system, restaurants keep more revenue per order, maintain direct customer relationships, and have full control over pricing, promotions, and delivery logistics without middleman costs. The platform provides a complete solution for order management, customer communication, and delivery coordination.
Tech Stack
Premier League MVP Predictor
Description
A machine learning project that analyzes player statistics from the English Premier League to predict and determine who deservedly should become the MVP based on comprehensive performance metrics.
Problem
MVP selection in Fantasy Premier League is often subjective and doesn't account for all relevant performance metrics. Traditional selection methods may overlook players who contribute significantly across multiple statistical categories.
Solution
Using an XGBoost machine learning model trained on comprehensive player statistics (goals, assists, clean sheets, influence, creativity, threat, etc.), the system objectively predicts player value and identifies the top 25 MVP candidates based on data-driven analysis rather than subjective opinion.
