Case study
McDonalds Ideal Calorie Menu
A nutrition analysis of the McDonald's menu that recommends a meal from it based on a person's age and gender, with the macronutrient reasoning shown.
Overview
Analyses a fast food menu against nutritional requirements by age and gender, computes the calories and the recommended balance of meat, vegetables, carbohydrates, sugars and proteins, and recommends a menu that fits.
One of the analyses produced under the data-driven content contract.
What I own
The analysis, the model and the visualisations.
Complexities tackled
A recommendation is a constrained optimisation, not a lookup. Picking items that hit a calorie target is easy and produces nonsense. Hitting a calorie target while keeping protein, carbohydrate and sugar within their own bands is a different problem, and it is the one that produces an answer a person could actually eat.
Requirements vary by person, so the output has to as well. Age and gender change the targets, which means the analysis produces a family of answers rather than one, and the presentation has to make clear which answer applies to whom.
Menu data is inconsistent by nature. Portion sizes, combined items and optional extras all make the same nominal item carry different numbers, and normalising that is most of the work before any analysis can start.
Stack
Python with Pandas and NumPy for the modelling, Matplotlib for the charts.
Working on something similar?
Tell me what you are building and what is in the way. I will tell you honestly whether I am the right person for it.