Insights from machine-learned diet success prediction
Conference Proceeding Article
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 di erence 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.
Calorie counting, MyFitnessPal, Quantified self, Weight loss
Dynamic Systems | Software Engineering
Proceedings on 21st Pacific Symposium on Biocomputing: PSB 2016, Fairmont OrchidBig Island, United States, 2016 January 4-8
World Scientific Publishing Co. Pte Ltd
City or Country
WEBER, Ingmar and ACHANANUPARP, Palakorn, "Insights from machine-learned diet success prediction" (2016). Research Collection School of Social Sciences. Paper 2128.
Available at: http://ink.library.smu.edu.sg/soss_research/2128
This document is currently not available here.