// multi-utility computation suite · offline · instant · precise
┌──────────────────────────┐
│ [c] calcalyst_ │
│ computation suite │
└──────────────────────────┘
// select a module to initialize
/ search↵ open firstesc close
// adsenseEMPTY_LEADER_SLOT728×90
// adsenseMOBILE_ANCHOR_SLOT320×50
// keyboard_shortcuts
/focus search
↑↓navigate module list
Enter
open first result from search
open highlighted
compute when module is open
compute when focused in a field
Escclose module · clear selection
⌫
dev.recommendation-system-metrics Calculator
Calculates recommendation system quality metrics — precision@k, recall@k, NDCG, and coverage — from recommendation lists and ground truth. NDCG (Normalised Discounted Cumulative Gain) weights higher-ranked recommendations more heavily — it's the standard metric for ordered recommendation lists.
Inputs
Relevant Items
Reference formula or conversion factor shown for context.
Retrieved K
Reference formula or conversion factor shown for context.
True Positives
Reference formula or conversion factor shown for context.
Reciprocal Rank Position
Reference formula or conversion factor shown for context.
Results
Precision@K
Sample size or count used in the calculation.
Recall@K
Reference formula or conversion factor shown for context.
F1@K
Reference formula or conversion factor shown for context.
MRR (mean reciprocal rank)
Arithmetic average — sum divided by count. Simple and familiar, but pulled by outliers. If your data contains extreme values, the median may be more representative.
NDCG
Sample size or count used in the calculation.
K
Reference formula or conversion factor shown for context.