Name Matching Python Packages

fuzzyname

A simple python class for fuzzy name matching

indic-namematch

Name matching for Indian identity documents: initials, transliteration, patronymics, honorifics and OCR noise. Pure stdlib, no dependencies.

tidyname

Intelligent company name cleaning and normalization for Python. Entity resolution for messy data with fuzzy matching.

name-variants

Multilingual name romanization lookup across Chinese, Japanese, Korean, Arabic, Vietnamese, and more. Resolves whether two name spellings refer to the same person — Chan/Chen/陈, Hsu/Xu, Chou/Zhou — across Pinyin, Wade-Giles, Cantonese, Hokkien, and other romanization systems.

eridu

Deep fuzzy matching people and company names for multilingual entity resolution using representation learning

search-names

Search a long list of names (patterns) in a large text corpus systematically and quickly

company-name-matcher

A library for matching and comparing company names using a fine-tuned sentence transformer model

sanctions-screening-benchmark

Reproducible benchmark for sanctions name-screening effectiveness. Measures recall across 18 documented classes of name variation — transliteration, Unicode homoglyph evasion, OCR degradation — with synthetic negative controls