Data Analyst — FoodImage

The FoodImage smartphone app transmits users' photographs of food selection and food waste to researchers and includes user-tagged information about waste reasons and destinations. Twenty-four participants were trained to record food waste using FoodImage, food waste diaries requiring visual estimation of waste quantities, and diaries requiring scale weights. In a randomized crossover trial, participants used each method during three staged food-waste scenarios (food preparation, eating, and clean-out).

Disparate data source mapping. Linked Standard Reference 28 (SR28) with the Food and Nutrient Database for Dietary Studies (FNDDS) to get accurate food waste estimations using Amazon Relational Database Service (AWS RDS.)
Displayed results using a Django-based website. Hosted on Amazon Elastic Compute Cloud Instances (AWS EC2).
Used linear regression machine learning algorithm in Python for outlier detection.