Download PDF
Welcome to Rosette Match Studio, an interactive tool for evaluating and optimizing Rosette name matching.
Rosette Match Studio includes the following components:
-
Upload Index Upload a file containing your data. This list of people, organizations, and/or locations is the index.
-
Search Search the index for matches using search terms.
-
Compare Display the details of a pairwise match (a match between two names), including the algorithms used to calculate the match scores. Modify the values of match parameters and see the impact on the match score. Use these values to optimize the settings for your data.
-
Evaluate Perform name matching on a file of names, benchmarking, and testing of your match parameters with your index.
-
Configuration View and modify search settings and field data types.
-
Help This help file.
Your business determines your specific use case and priorities. Search can be optimized to balance accuracy by trading off high recall (never miss a match at the expense of some false positives) with high precision (reduce false positives with a slightly higher risk of missing a match) along with search speed to get the results you need for your use case. Required resources will depend on the size of your datasets, the required throughput, and your target accuracy levels.
Matching is the process of determining whether identifying information about an individual, such as their name, company, address, and/or age, matches a record in the index. With Rosette Match Studio, you can enter one or more pieces of identifying information and produce a list of potential matches. Each match will have a score, between 0 and 100%, indicating the strength of the match.
Name matching is the core of matching. Names are complex to match because of the large number of variations that occur within a language and across languages. These include, but are not limited to, typographical errors, phonetic spelling variations, transliteration differences, initials, and nicknames.
Rosette Match Studio also matches other Field Types, such as organization name, location name, and date.
You can investigate why particular fields matched and how scores were calculated using the compare functionality. You can change how the scores are calculated by modifying the match parameters in real-time, to better understand the process and tune it for your specific application.
Rosette Match Studio can identify name similarities between English and all supported languages. Cross language matches are supported between Chinese, Japanese, and Korean. Matching names in the same language is supported for all languages.
Table 1. Supported Languages
|
Arabic (ara)
|
Greek (ell)
|
Portuguese (por)
|
|
Chinese, Simplified (zho)
|
Hungarian (hun)
|
Pashto (pus)
|
|
Chinese, Traditional (zho)
|
Italian (ita)
|
Russian (rus)
|
|
English (eng)
|
Japanese (jpn)
|
Spanish (spa)
|
|
French (fra)
|
Korean (kor)
|
Thai (tha)
|
|
German (deu)
|
Persian/Farsi (fas ): Dari(prs ) and Western (pes)
|
Urdu (urd)
|
Examples of Supported Matches
-
English - English (same language)
-
Chinese - Korean (cross language match for Chinese, Japanese, and Korean)
-
Hungarian - English (English - language match)
-
Hungarian - Hungarian (same language)
Types of Token and Name Matches