Inspiration
We were given a data set by Mai Shan Yun and we wanted to help them optimize their sales
What it does
-Shortage flags show where usage exceeded shipments, revealing potential stockout risks, shrinkage, theft, or supplier failures -Surplus flags identify overstocked items tying up cash and risking spoilage -Links point-of-sale data (menu sales) directly to ingredient consumption via standardized recipes -Compares actual usage against what was received, exposing discrepancies -Creates an audit trail from menu item to raw material flow -Identifies data quality issues (missing shipments, recording errors) -Shows which menu items drive the most ingredient consumption -Reveals operational bottlenecks—high-selling items that strain ingredient supply chains -Enables menu redesign decisions -Detects periods where usage spikes don't align with shipment timing -Identifies if May was high-demand but shipments arrived in June -Connects spending directly to actual consumption -Surfaces supplier renegotiation opportunities for high-cost, high-usage items -Forecasts future ingredient needs based on historical menu demand -Prevents both stockouts and excess ordering -Tracks supplier reliability metrics (delivery delays, frequency consistency) -Flags vendors causing inventory imbalances
How we built it
Merging data sets and mapping it to the ingredients and the shipment dataset to create dash boards and a predictive model
Challenges we ran into
Data visualization, predictive model generation, data mapping
Accomplishments that we're proud of
Successfully mapping data and data visualization, collecting all the data together
What we learned
Data cleaning is a crucial step(It must be precise), standardization
What's next for MSY Challenge
Implementing a Gemini API to recommend the user
Log in or sign up for Devpost to join the conversation.