March Edition: Data and the Food We Eat (and Drink, and Measure)

Cooking, like data science, blends together rules and rule-breaking, precise measures and creativity

TDS Editors
Towards Data Science

--

Photo by Giorgio Trovato on Unsplash

When we follow a recipe, are we essentially taking an algorithm or ML model to production? Is fine-tuning hyperparameters just like dipping a spoon into a pot of simmering broth to check it’s well-seasoned? Is the smoke coming out of your oven… metadata? These may sound like silly questions to you, an accomplished data professional, but they make a lot of sense to me, an editor who used to hate math but always loved cooking.

People often tell us to step out of our comfort zone, but for this Monthly Edition—coinciding with the second anniversary of a pandemic and a world very much not at peace—tiptoeing right back into that zone feels warranted, or at least understandable. I hope you’ll humor my passion for good bread and shaky analogies and come along to sample some of the best TDS articles at the intersection of data science and food.

As is always the case once you start digging your way through the TDS archives, choosing was hard. Some of the picks below are passion projects that take us down data-driven culinary rabbit holes (real rabbits harmed along the way: zero). Others use food as a point of departure to explore programming, machine learning, and the internet of things (IoT). None of them discuss dumplings, which is a shame; if you’re sitting on some cutting-edge data science research on varenyky, gyoza, manti, or any of their plump cousins, please send it our way. (If you’re sitting on some cutting-edge research on other topics, please send it our way, too.)

Wishing you all a safe and peaceful month,

Ben Huberman, Editor in Chief

The Great British Baking Show: Random Forests Edition

Introducing random forests step-by-step so you can see every ingredient as it’s combined.

By Pamela Wu (8 minutes)

Double-Blind Coffee Studies

An espresso expert discusses why they avoid a standard testing method.

By Robert McKeon Aloe (6 minutes)

Fermenting Data Visualization

A Summer of self-directed Python learning.

By Ross Wait (10 minutes)

The Data Scientist’s Guide To Buying Wine

Isolating the chemicals that make wine great.

By Barbara Vanaki (7 minutes)

Urban Health: Predicting Food Insecurity in Developing Countries (Part 2)

Can we apply machine learning techniques to start addressing a major global concern?

By Dea Bardhoshi (7 minutes)

Making better cheese with IoT and ML

Optimise the cheese-making process using low-cost IoT and machine learning solutions.

By Coenraad Pretorius (14 minutes)

Measuring Meals’ Similarities

Applying Word2Vec in the food domain to generate food embeddings.

By Yaron Vazana (4 minutes)

AI-Designed “Hyperfoods” Can Possibly Help Prevent Cancer

Modern machine learning techniques can discover bioactive molecules, some of which are similar to anti-cancer drugs, and help design nutrition that will let us live longer and healthier.

By Michael Bronstein, Kirill Veselkov, and Gabriella Sbordone (14 minutes)

Thank you for joining us this month — and for all your generous support of our authors, including our newest cohort, joining us in February: say hello to Salih Salih, Alexander Wei, Antoine Villatte, Kieron Spearing, Jean-marc Buchert, Leah Simpson and Ray McLendon, Nicolás García Aramouni, Martim Chaves, Dan Schauder, Kaan Bıçakcı, Mrinal Gupta, Prateek Chhikara, Albert Wibowo, Maisie (Margaret) Moore, Benjamin Fuhrer, Mohamed Amine HACHICHA, Pedro Ferrari, Jeffrey Näf, Hussein Abdulrahman, Zack Fizell, Nura Kawa, Louis Magowan, Bahar Salehi, Ville Tuulos, Oscar Leo, Niklas Lang, Casey Cheng, Valerias Bangert, Viyaleta Apgar, Adam Kovacs, Leon Sun, Alvin Chan, Andrii Gozhulovskyi, Andrew Joseph Davies, J. Rafid S., PhD, Tamas K Stenczel, Mert Gökalp, PhD, C. Golo Naito, Grzegorz Sikora, Satoru Hayasaka, Subrahmanya Joshi, Giulia Vilone, Vijay Yadav, Ivy Liu, Gustav Šír, Roland Schätzle, Richard Roberts, Martin Habedank, Perceval Desforges, Nathan Sutton, Jason Platt, Ankita Sinha, Ivan Duspara, Ahmed Fahim, Asya Frumkin, Ikenna Ogbogu, Robin Opdam, Daniel Fein, Tarek Samaali, Avi Chad-Friedman Victor Delvigne, Ansh Bordia, Lars ter Braak, Roberto Zappa, Marc Velay, Dávid Guszejnov, Jonathan Serrano, Katy Hagerty, Adrian Causby, Sage Elliott, Adithya Krishnan, Meraldo Antonio, Graham McNicoll, Kruthi Krishnappa, Andreas Martinson, Leonardo Cavagnis, Yaniv Vaknin, Luca Clissa, Luca Reeb, Slava Kisilevich, Utkarsh Lal, Juras Juršėnas, Jeremy Neiman, Josh Bickett, Maya A., Paul J. Blazek, and Richie Bachala, among others.

--

--

Building a vibrant data science and machine learning community. Share your insights and projects with our global audience: bit.ly/write-for-tds