GroceryDB

Looks like the data is available for download here: https://github.com/Barabasi-Lab/GroceryDB They also normalized the data for nutritional facts per 100grams which is super interesting IMO.

https://github.com/Barabasi-Lab/GroceryDB > we introduce GroceryDB, a database with over 50,000 food items sold by Walmart, Target, and Wholefoods, unveiling the degree of processing characterizing each food. GroceryDB indicates that 73% of the US food supply is ultra-processed, and on average ultra-processed foods are 52% cheaper than minimally-processed alternatives. We find that the nutritional choices of the consumers, translated as the degree of food processing, strongly depend on the food categories and grocery stores. We show that there is no single nutrient or ingredient "bio-marker" for ultra-processed food, allowing us to quantify the individual contribution of over 1,000 ingredients to ultra-processing. GroceryDB and the associated https://www.TrueFood.tech website make this information available, aiming to simultaneously empow

The research database yesterday on GitHub: https://github.com/Barabasi-Lab/GroceryDB The research paper: https://www.medrxiv.org/content/10.1101/2021.05.22.21257615v... Per the Washington Post: > If you need the convenience of ultra-processed foods, you can check labels and comparison shop. Try to pick the products with the fewest ingredients. For help while shopping, you can pull up a website on your phone called truefood.tech. On the site you can type in a food that you want to buy — such as chicken nuggets or breakfast cereal — and in response the site will show you dozens of brands and recommend the least processed versions. The site uses machine learning to rank foods on a scale of 1 to 100 based on factors such as how many additives they contain and their degree of processing. The lower the score the better. > The site was created b