Measured pairing · from 63,696 recipes

What goes with pork?

Measured across 63,696 recipes, the 8 ingredients that co-occur with pork most disproportionately are sauerkraut (×6.3 chance, n=50), chinese cabbage (×5.0 chance, n=32), veal (×4.9 chance, n=40), celery oil (×4.7 chance, n=174), lima bean (×4.6 chance, n=28), star anise (×4.0 chance, n=21), soy sauce (×3.6 chance, n=564) and cider (×3.5 chance, n=145). 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. sauerkraut — PPMI 1.83 · ×6.3 chance · n=50 (sauerkraut itself appears in 216 recipes)
  2. chinese cabbage — PPMI 1.61 · ×5.0 chance · n=32 (chinese cabbage itself appears in 172 recipes)
  3. veal — PPMI 1.58 · ×4.9 chance · n=40 (veal itself appears in 222 recipes)
  4. celery oil — PPMI 1.54 · ×4.7 chance · n=174 (celery oil itself appears in 1,008 recipes)
  5. lima bean — PPMI 1.53 · ×4.6 chance · n=28 (lima bean itself appears in 164 recipes)
  6. star anise — PPMI 1.39 · ×4.0 chance · n=21 (star anise itself appears in 142 recipes)
  7. soy sauce — PPMI 1.27 · ×3.6 chance · n=564 (soy sauce itself appears in 4,263 recipes)
  8. cider — PPMI 1.24 · ×3.5 chance · n=145 (cider itself appears in 1,135 recipes)

Cook the pairing

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

How this was measured

pork appears in 2,357 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.