Measured pairing · from 63,696 recipes

What goes with basil?

Measured across 63,696 recipes, the 8 ingredients that co-occur with basil most disproportionately are mozzarella cheese (×7.0 chance, n=676), savory (×6.4 chance, n=53), oregano (×6.3 chance, n=1407), rosemary (×5.7 chance, n=743), macaroni (×4.9 chance, n=1023), cured pork (×4.9 chance, n=100), romano cheese (×4.6 chance, n=88) and parmesan cheese (×4.5 chance, n=1058). 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. mozzarella cheese — PPMI 1.94 · ×7.0 chance · n=676 (mozzarella cheese itself appears in 1,484 recipes)
  2. savory — PPMI 1.85 · ×6.4 chance · n=53 (savory itself appears in 128 recipes)
  3. oregano — PPMI 1.84 · ×6.3 chance · n=1407 (oregano itself appears in 3,429 recipes)
  4. rosemary — PPMI 1.73 · ×5.7 chance · n=743 (rosemary itself appears in 2,014 recipes)
  5. macaroni — PPMI 1.60 · ×4.9 chance · n=1023 (macaroni itself appears in 3,181 recipes)
  6. cured pork — PPMI 1.58 · ×4.9 chance · n=100 (cured pork itself appears in 315 recipes)
  7. romano cheese — PPMI 1.53 · ×4.6 chance · n=88 (romano cheese itself appears in 293 recipes)
  8. parmesan cheese — PPMI 1.50 · ×4.5 chance · n=1058 (parmesan cheese itself appears in 3,628 recipes)

Cook the pairing

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

How this was measured

basil appears in 4,153 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.