Matchcode Optimization:Overlap Coefficient

From Melissa Data Wiki
Revision as of 23:49, 25 September 2018 by Admin (talk | contribs) (Created page with "{{MatchcodeOptimizationNav |AlgorithmsCollapse= }} ==Overlap Coefficient== ===Specifics=== *https://en.wikipedia.org/wiki/Overlap_coefficient ===Summary=== Like Jaro or Dice...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

← MatchUp Hub

Matchcode Optimization Navigation
Matchcode Optimization
First Component
Fuzzy Algorithms
Swap Matching
Blank Matching
Advanced Component Types
Algorithms
Accunear
Alphas
Consonants
Containment
Dice's Coefficient
Double Metaphone
Exact
Fast Near
Frequency
Frequency Near
Jaccard Similarity Coefficient
Jaro
Jaro-Winkler
Longest Common Substring (LCS)
MD Keyboard
Needleman-Wunsch
N-Gram
Numeric
Overlap Coefficient
Phonetex
Smith-Waterman-Gotoh
Soundex
UTF8 Near
Vowels


Overlap Coefficient

Specifics

Summary

Like Jaro or Dice, counts matching n-Grams (discarding duplicate NGRAMs), but uses a slightly different calculation weighted towards the smaller of the two strings being compared.

Returns

Percentage of similarity

Union/MinNumNGrams

Where union is defined as the number of matching NGAMS found

Where minNumNGrams is defined as the smallest number of possible NGRAMS of the two strings

NGRAM is defined as the size of the substring to search for within a string (default is 2).

Example Matchcode Component

MCO Algorithm OverlapCoefficient.png

Example Data

STRING1 STRING2 RESULT
Johnson Jhnsn Unique
Neumon Pneumon Match Found
Maytown Hs Maytown Public Schools Match Found
Rober Roberts Match Found



Performance
Slower Faster
Matches
More Matches Greater Accuracy


Recommended Usage

Hybrid deduper, where a single incoming record can quickly be evaluated independently against each record in an existing large master database.

Databases created with abbreviations or similar word substitutions.

Not Recommended For

Large or Enterprise level batch runs. Since the algorithm must be evaluated for each record comparison, throughput will be very slow.

Databases created via real-time data entry where audio likeness errors are introduced.

Do Not Use With

UTF-8 data. This algorithm was ported to MatchUp with the assumption that a character equals one byte, and therefore results may not be accurate if the data contains multi-byte characters.