Measured pairing · from 63,696 recipes

What goes with black bean?

Measured across 63,696 recipes, the 8 ingredients that co-occur with black bean most disproportionately are chili powder (×10.6 chance, n=25), kidney bean (×10.3 chance, n=51), avocado (×8.1 chance, n=59), cilantro (×7.6 chance, n=208), cumin (×6.9 chance, n=248), chickpea (×5.4 chance, n=24), corn (×4.6 chance, n=221) and cayenne (×4.3 chance, n=347). 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. chili powder — PPMI 2.36 · ×10.6 chance · n=25 (chili powder itself appears in 246 recipes)
  2. kidney bean — PPMI 2.33 · ×10.3 chance · n=51 (kidney bean itself appears in 518 recipes)
  3. avocado — PPMI 2.10 · ×8.1 chance · n=59 (avocado itself appears in 755 recipes)
  4. cilantro — PPMI 2.03 · ×7.6 chance · n=208 (cilantro itself appears in 2,851 recipes)
  5. cumin — PPMI 1.94 · ×6.9 chance · n=248 (cumin itself appears in 3,730 recipes)
  6. chickpea — PPMI 1.68 · ×5.4 chance · n=24 (chickpea itself appears in 465 recipes)
  7. corn — PPMI 1.53 · ×4.6 chance · n=221 (corn itself appears in 4,964 recipes)
  8. cayenne — PPMI 1.46 · ×4.3 chance · n=347 (cayenne itself appears in 8,371 recipes)

Cook the pairing

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

How this was measured

black bean appears in 611 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.