Guidelines to Improve Prediction Accuracy

In order to get the most accurate prediction of address components, your input address strings should adhere to these patterns.

Guidelines for Australia Addresses

Avoid non-address components
Presence of non-address components in the input string might lead to wrong prediction. Remove such components before feeding the string for prediction.
Maintain a sequence in address components
The address components should be placed in this order: OrganizationName > AddressNumber > Street > PostCode > City > StateProvince > Country.
Example:
  • Incorrect: Level 5 176 Messines Ridge Rd Griffith College Mount Gravatt QLD 4122 Australia
  • Correct: Griffith College Level 5 176 Messines Ridge Rd Mount Gravatt QLD 4122 Australia
Remove redundant address components
The input address string should not have repeated address components, such as two different organization names or repetitive name of an organization in one string.
Example: Griffith College Level 5 176 Messines Ridge Rd Griffith College Mount Gravatt QLD 4122 Australia
Do not have merged components in address strings
Merged address components result in incorrect prediction.
Example:
  • Incorrect: Griffith College Level-5-176 Messines Ridge Rd Mount Gravatt QLD 4122 Australia
  • Correct: Griffith College Level 5 176 Messines Ridge Rd Mount Gravatt QLD 4122 Australia
Avoid addressee name in the string
Addressee name in the string results in incorrect prediction for the Australia addresses.
Example:
  • Incorrect: Alice Smith Griffith College Level 5 176 Messines Ridge Rd Mount Gravatt QLD 4122 Australia
  • Correct: Griffith College Level 5 176 Messines Ridge Rd Mount Gravatt QLD 4122 Australia
Do not have bracketed "()" address component
Including any of your address components inside brackets "()" will leave it unparsed.
Example: Griffith College (Level 5) 176 Messines Ridge Rd Mount Gravatt QLD 4122 Australia

Limitations for Australia Addresses

These are the limitations of the address parser for Australia addresses:
  • PO Box addresses are not supported.
  • Sentence specific addresses (for example, addresses containing "close to", "between", "nearby") are not supported.

    Example: Tourquay Road Close To Butcher Shop Hervey Bay QLD 4655 AUS

  • Addresses containing roads with "and" or "&" are not supported.

    Example: Corner Farrall Road and O'Connor Road Stratton 6056 AUS

  • Addresses with a complex street format (for example, extra street information like tower, park, and building) are not supported.

    Example: Wesfarmers Limited Level 14 Brookfield Place Tower 2 123 St Georges Terrace Perth 6000 AUS

  • Unit/street components in character format are not supported.

    Example: Ground Floor 46 Charlotte St Brisbane 4000 AUS

  • Avoid repeating words for Org, state, or country in addresses (for example, Australia or QLD).

    Example: DOF Subsea Australia Pty Ltd 5th FL 181 St Georges TCE Perth Western Australia 6000 AUS

Guidelines for Canada Addresses

Avoid non-address components
Presence of non-address components in the input string might lead to wrong prediction. Remove such components before feeding the string for prediction.
Maintain a sequence in address components
The address components should be placed in this order: OrganizationName > AddressNumber > Street > PostCode > City > StateProvince > Country.
Example:
  • Incorrect: 127 ORR AVE L4L9K2 ON WOODBRIDGE CAN
  • Correct: 127 ORR AVE L4L9K2 WOODBRIDGE ON CAN
Remove redundant address components
The input address string should not have repeated address components, such as two different organization names or repetitive name of an organization in one string.
Example: Adlib Publishing Systems Inc Adlib Publishing Systems Inc 10 5100 South Service Rd Burlington ON Canada
Do not have merged components in address strings
Merged address components result in incorrect prediction.
Example:
  • Incorrect: Adlib-Publishing-Systems-Inc-10 South Service Rd Burlington ON Canada
  • Correct: Adlib Publishing Systems Inc-10 South Service Rd Burlington ON Canada
Avoid addressee name in the string
Address name in the string results in incorrect prediction for the Canada addresses.
Example:
  • Incorrect: Mr. XXX Adlib Publishing Systems Inc 10 5100 South Service Rd Burlington ON Canada
  • Correct: Adlib Publishing Systems Inc 10 5100 South Service Rd Burlington ON Canada
Do not have bracketed "()" address component
Including any of your address components inside brackets "()" will leave it unparsed.
Example: (Adlib Publishing Systems Inc) 10 5100 South Service Rd Burlington ON Canada

Limitations for Canada Addresses

These are the limitations of the address parser for Canada addresses:
  • Unit or Apartment information is not supported.
  • French characters present in the address are not displayed correctly.

Guidelines for France Addresses

Avoid non-address components
Presence of non-address components in the input string might lead to wrong prediction. Remove such components before feeding the string for prediction.
Maintain a sequence in address components
The address components should be placed in this order: OrganizationName > AddressNumber > Street > PostCode > City > StateProvince > Country.
Example:
  • Incorrect: Normandie Hôtel 236 Rue Denis Papin Barentin Seine-Maritime 76360 France
  • Correct: Normandie Hôtel 236 Rue Denis Papin 76360 Barentin Seine-Maritime France
Remove redundant address components
The input address string should not have repeated address components, such as two different organization names or repetitive name of an organization in one string.
Example: School André Marie 351 Boulevard de Normandie 76360 André Marie Barentin France
Do not have merged components in address strings
Merged address components result in incorrect prediction.
Example:
  • Incorrect: School-André-Marie 351 Boulevard de Normandie 76360 Barentin Seine-Maritime France
  • Correct: School André Marie 351 Boulevard de Normandie 76360 Barentin Seine-Maritime France
Avoid addressee name in the string
Address name in the string results in incorrect prediction for the France addresses.
Example:
  • Incorrect: Mr. XXXXX School André Marie 351 Boulevard de Normandie 76360 Barentin Seine-Maritime France
  • Correct: School André Marie 351 Boulevard de Normandie 76360 Barentin Seine-Maritime France
Do not have bracketed "()" address component
Including any of your address components inside brackets "()" will leave it unparsed.
Example: School (André Marie) 351 Boulevard de Normandie 76360 Barentin Seine-Maritime France

Limitations for France Addresses

These are the limitations of the address parser for France addresses:
  • Streets including city name are not supported.

    Example: 14 Rue de Maule 78870 Bailly France

  • The overseas regions of France are incorrectly parsed (for example, Martinique, Réunion, and Guadeloupe).

Guidelines for German Addresses

Avoid non-address components
Presence of non-address components in the input string might lead to wrong prediction. Remove such components before feeding the string for prediction.
Maintain a sequence in address components
The address components should be placed in this order: OrganizationName > Floor > PlaceName > AddressNumber > Street > Neighbourhood > City/Suburb/County > PostCode > Country.
Example:
  • Incorrect: 3 Weseler Strasse 46514 Schermbeck DEU
  • Correct: Weseler Strasse 3 46514 Schermbeck DEU
Remove redundant address components
The input address string should not have repeated address components, such as two different organization names or repetitive name of an organization in one string.
Example: Weseler Strasse 3 Weseler Strasse 46514 Schermbeck DEU
Ensure address number and street name are included
Your address string needs to have address number and street name. Missing out these essential address components will impact the accuracy of the result.
Example:
  • Incorrect: 46514 Schermbeck DEU
  • Correct: Weseler Strasse 3 46514 Schermbeck DEU
Do not have merged components in address strings
Merged address components result in incorrect prediction.
Example:
  • Incorrect: Weseler-Strasse-3 46514 Schermbeck DEU
  • Correct: Weseler Strasse 3 46514 Schermbeck DEU
Avoid addressee name in the string
Addressee name in the string results in incorrect prediction for the German addresses.
Example:
  • Incorrect: Mr John Doe Weseler Strasse 3 46514 Schermbeck DEU
  • Correct: Weseler Strasse 3 46514 Schermbeck DEU
Do not have bracketed "()" address component
Including any of your address components inside brackets "()" will leave it unparsed.
Example: Weseler Strasse 3 46514 (Schermbeck) DEU

Guidelines for Spain Addresses

Avoid non-address components
Presence of non-address components in the input string might lead to wrong prediction. Remove such components before feeding the string for prediction.
Maintain a sequence in address components
The address components should be placed in this order: OrganizationName > Street > AddressNumber > PostCode > City > StateProvince > Country.
Example:
  • Incorrect: Calle San Fernando 4 University of Seville 41004 Sevilla Spain
  • Correct: University of Seville Calle San Fernando 4 41004 Sevilla Spain
Remove redundant address components
The input address string should not have repeated address components, such as two different organization names or repetitive name of an organization in one string.
Example: University of Seville Calle San Fernando 4 University of Seville 41004 Sevilla Spain
Do not have merged components in address strings
Merged address components result in incorrect prediction.
Example:
  • Incorrect: University of Seville Calle-San-Fernando 4 41004 Sevilla Spain
  • Correct: University of Seville Calle San Fernando 4 41004 Sevilla Spain
Avoid addressee name in the string
Addressee name in the string results in incorrect prediction for Spain addresses.
Example:
  • Incorrect: Francisco Rodríguez University of Seville Calle San Fernando 4 41004 Sevilla Spain
  • Correct: University of Seville Calle San Fernando 4 41004 Sevilla Spain
Do not have bracketed "()" address component
Including any of your address components inside brackets "()" will leave it unparsed.
Example: University of Seville (Calle San Fernando) 4 41004 Sevilla Spain

Limitations for Spain Addresses

These are the limitations of the address parser for Spain addresses:
  • Addresses starting with an abbreviation (for example, PL., Av., BL., C.) addresses are not supported.
  • Streets including landmark information (for example, At, Near, Between) are not supported.

Guidelines for United Kingdom Addresses

Avoid non-address components
Presence of non-address components in the input string might lead to wrong prediction. Remove such components before feeding the string for prediction.
Maintain a sequence in address components
The address components should be placed in this order: OrganizationName > Floor > PlaceName > AddressNumber > Street > Neighbourhood > City/Suburb/County > PostCode > Country.
Example:
  • Incorrect: Widget Limited London Milenium street Unit 3 AB10 3DF GBR
  • Correct: Widget Limited Unit 3 Milenium street London AB10 3DF GBR
Remove redundant address components
The input address string should not have repeated address components, such as two different organization names or repetitive name of an organization in one string.
Example:
  • Incorrect: Widget Limited Widget Limited Unit 10 Logix Cyber Park 10 Manor Street London AB10 3DF GBR
Follow single-token organization names with organization type
A single-token organization name should be followed by the type of the organization, such as Ltd, Inc, and Reg. In the example below, Ardian is a single-token organization name. In this case, the organization name is not followed by the type "Limited," and the results may be inaccurate.
Example:
  • Incorrect: Ardian Fourth Floor Channel House St Helier Je2 4UH GBR
  • Correct: Ardian Limited Fourth Floor Channel House St Helier Je2 4UH GBR

Limitations for United Kingdom Addresses

An address string of any of these kind is susceptible to getting inaccurately predicted by the address parser. Watch out for these in your address strings.

Presence of another address component as name of the organization
If the name of the organization includes any other address component, such as Floor, Flat, and House, the prediction accuracy may be affected.
Example: Flat Seasons 632 Kings Road London Middlesex SW6 2DU GBR
Organization name having numbers
If an organization name has numbers, it is susceptible to getting erroneously predicted.
Example: 123 Limited ABC Street AB10 3DF GBR

Guidelines for United States Addresses

Avoid non-address components
Presence of non-address components in the input string might lead to wrong prediction. Remove such components before feeding the string for prediction.
Maintain a sequence in address components
The address components should be placed in this order: OrganizationName > AddressNumber > Street > City > StateProvince > PostCode > Country.
Example:
  • Incorrect: 2200 Western CT Widget USA Lisle IL 60532
  • Correct: Widget 2200 Western CT Lisle IL 60532 USA
Remove redundant address components
The input address string should not have repeated address components, such as two different organization names or repetitive name of an organization in one string.
Example: Widget 2200 Western CT Widget Lisle IL 60532 USA
Do not have merged components in address strings
Merged address components result in incorrect prediction.
Example:
  • Incorrect: Widget-Ltd-2200 Western CT Lisle IL 60532 USA
  • Correct: Widget Ltd 2200 Western CT Lisle IL 60532 USA
Avoid addressee name in the string
Addressee name in the string results in incorrect prediction for the United States addresses.
Example:
  • Incorrect: Mr John Doe Widget 2200 Western CT Lisle IL 60532 USA
  • Correct: Widget 2200 Western CT Lisle IL 60532 USA
Do not have bracketed "()" address component
Including any of your address components inside brackets "()" will leave it unparsed.
Example: Widget 2200 Western CT (Lisle) IL 60532 USA

Limitations for United States Addresses

These are the limitations of the address parser for United States addresses:
  • PO Box addresses are not supported.
  • In Care of (C/O) addresses are not supported.
  • If AddressNumber is missing, StreetNumber may be returned as AddressNumber (only in cases of numeric digits without superscripts).
  • Direction may be returned in StateProvince for a few defined addresses (especially in cases where Direction is comprised of two letters).