Insights from Machine-Learned Diet Success Prediction

TL;DR

This study analyzes public food diaries from over 4,000 MyFitnessPal users to predict diet success using machine learning, revealing both expected and novel dietary indicators influencing calorie goals.

Contribution

It introduces the first systematic analysis of public food diaries for diet success prediction using machine learning techniques.

Findings

Certain food categories like desserts indicate over-calorie intake.

Differences between pork and poultry relate to dieting success.

Use of quick calorie addition correlates with calorie overshoot.

Abstract

To support people trying to lose weight and stay healthy, more and more fitness apps have sprung up including the ability to track both calories intake and expenditure. Users of such apps are part of a wider ``quantified self'' movement and many opt-in to publicly share their logged data. In this paper, we use public food diaries of more than 4,000 long-term active MyFitnessPal users to study the characteristics of a (un-)successful diet. Concretely, we train a machine learning model to predict repeatedly being over or under self-set daily calories goals and then look at which features contribute to the model's prediction. Our findings include both expected results, such as the token ``mcdonalds'' or the category ``dessert'' being indicative for being over the calories goal, but also less obvious ones such as the difference between pork and poultry concerning dieting success, or the use of the ``quick added calories'' functionality being indicative of over-shooting calorie-wise. This study also hints at the feasibility of using such data for more in-depth data mining, e.g., looking at the interaction between consumed foods such as mixing protein- and carbohydrate-rich foods. To the best of our knowledge, this is the first systematic study of public food diaries.