Measured pairing · from 63,696 recipes

What goes with coffee?

Measured across 63,696 recipes, the 8 ingredients that co-occur with coffee most disproportionately are cocoa (×7.9 chance, n=428), rum (×6.9 chance, n=48), brandy (×4.4 chance, n=21), vanilla (×3.5 chance, n=357), cream (×2.9 chance, n=334), buttermilk (×2.5 chance, n=48), milk (×2.3 chance, n=347) and milk fat (×2.1 chance, n=23). The score behind the ranking is positive pointwise mutual information — how many times more often a pair shares a recipe than random combination would predict — and n is the number of recipes containing both ingredients. Nothing is published below a floor of 20 recipes per pair and 100 per ingredient. Co-occurrence records what recipe authors actually do — it conflates deliciousness with popularity and tradition — so read it as ethnography, not judgment.

The measured partners — PPMI · ×chance · n

1. cocoa — PPMI 2.07 · ×7.9 chance · n=428 (cocoa itself appears in 4,807 recipes)
2. rum — PPMI 1.93 · ×6.9 chance · n=48 (rum itself appears in 621 recipes)
3. brandy — PPMI 1.49 · ×4.4 chance · n=21 (brandy itself appears in 420 recipes)
4. vanilla — PPMI 1.26 · ×3.5 chance · n=357 (vanilla itself appears in 9,032 recipes)
5. cream — PPMI 1.06 · ×2.9 chance · n=334 (cream itself appears in 10,243 recipes)
6. buttermilk — PPMI 0.93 · ×2.5 chance · n=48 (buttermilk itself appears in 1,682 recipes)
7. milk — PPMI 0.82 · ×2.3 chance · n=347 (milk itself appears in 13,577 recipes)
8. milk fat — PPMI 0.75 · ×2.1 chance · n=23 (milk fat itself appears in 962 recipes)

Cook the pairing

Dishes in Palate's live corpus that use coffee with one of its measured partners:

• Banh Flan (Vietnamese Creme Caramel) — with vanilla, milk
• Tiramisu — with buttermilk
• Bubble Tea (珍珠奶茶) — with milk
• Ca Phe Trung (Vietnamese Egg Coffee) — with milk
• Ca Phe Sua Da (Vietnamese Iced Coffee) — with milk
• Teh Tarik (Pulled Milk Tea) — with milk

How this was measured

coffee appears in 717 of the 63,696 recipes counted (5,296 parsed + 1,081 hand-curated + 57,319 from the dataset published with Ahn et al., 2011). PPMI = max(0, ln(count(A,B)·N / (count(A)·count(B)))), all counts over the same N; lift = e^PMI, which reads directly as "×chance." Staples (salt, sugar, flour, water) are excluded because sources under-record them, and pairs where one name contains the other are excluded as near-duplicates.

Read the numbers with their limits: the corpus is Western-skewed (90% of it is the largely North American and European recipe dataset published with Ahn et al.'s 2011 paper), so the absence of a pairing here proves nothing except who wrote the recipes down. PPMI favors the rare end even above the floor — a niche pair at n=22 can outrank a workhorse pair seen thousands of times, because common ingredients' huge counts divide the score down — so read PPMI and n together.

The full reference — 150 ingredients, top 8 partners each — lives at What actually goes with X.

Curious how these flavors fit your palate — take the short taste test →

Every number above is counted from recipes — pointwise mutual information over 63,696 of them — not chef interviews, model guesses, or reviews.