Recipe AI Series
Building an ML-powered meal planning system to solve the daily struggle of nutritious, varied cooking — from cosine similarity to LSTM to ChatGPT.
4 articles
Part 1: Solving the Daily Meal Planning Problem with Data
How I tackled the universal 'what's for dinner' problem over a decade ago using classical data science — cleansing 20,000 recipes, 200,000 ingredient records, and nutritional data into a unified ML-ready dataset.
Part 2: Finding 'Same Nutrition, Different Meal' with Cosine Similarity
Using cosine similarity on nutritional vectors to find recipes that match a target meal's nutrition profile but offer completely different flavors — at both the recipe and menu level.
Part 3: Predicting 'Non-Boring' Menus with LSTM Time Series
Reframing meal planning as a text generation problem — using LSTM neural networks with temperature-controlled sampling to predict diverse, non-repetitive menus from historical meal sequences.
Part 4: Transforming 20,000 Recipes with ChatGPT
Years after building the original ML pipeline, LLMs changed everything — using the ChatGPT API to simplify elaborate recipes into weeknight-friendly meals, and reflecting on a decade-long journey from cosine similarity to LSTM to GPT.