# Similarity Metrics: Pearson, Cosine, Adjusted Cosine, Jaccard — Full Math + NumPy

> Source: https://sukruyusufkaya.com/en/learn/oneri-sistemleri/similarity-metrikleri-pearson-cosine-jaccard
> Updated: 2026-05-13T13:29:35.122Z
> Category: Öneri Sistemleri
> Module: Module 5: Memory-Based Collaborative Filtering (k-NN)
**TLDR:** Foundation of all CF algorithms: 4 main similarity metrics. Pearson correlation (rating bias correction), cosine similarity (vector direction), adjusted cosine (user bias correction), Jaccard (binary implicit). Full mathematical derivation + from-scratch NumPy + MovieLens comparison.