Measured pairing · from 63,696 recipes

What goes with cumin?

Measured across 63,696 recipes, the 8 ingredients that co-occur with cumin most disproportionately are fenugreek (×16.8 chance, n=927), turmeric (×13.6 chance, n=1158), coriander (×13.1 chance, n=1412), black bean (×6.9 chance, n=248), chickpea (×6.6 chance, n=179), chili powder (×6.1 chance, n=88), lentil (×5.8 chance, n=91) and cilantro (×5.5 chance, n=911). 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. fenugreek — PPMI 2.82 · ×16.8 chance · n=927 (fenugreek itself appears in 942 recipes)
  2. turmeric — PPMI 2.61 · ×13.6 chance · n=1158 (turmeric itself appears in 1,457 recipes)
  3. coriander — PPMI 2.57 · ×13.1 chance · n=1412 (coriander itself appears in 1,841 recipes)
  4. black bean — PPMI 1.94 · ×6.9 chance · n=248 (black bean itself appears in 611 recipes)
  5. chickpea — PPMI 1.88 · ×6.6 chance · n=179 (chickpea itself appears in 465 recipes)
  6. chili powder — PPMI 1.81 · ×6.1 chance · n=88 (chili powder itself appears in 246 recipes)
  7. lentil — PPMI 1.76 · ×5.8 chance · n=91 (lentil itself appears in 267 recipes)
  8. cilantro — PPMI 1.70 · ×5.5 chance · n=911 (cilantro itself appears in 2,851 recipes)

Cook the pairing

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

How this was measured

cumin appears in 3,730 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.