MyHeritage publishes massive collection of historical American city directories


TEL AVIV, Israel & LEHI, Utah – (COMMERCIAL THREAD) – MyHeritage, the world’s leading service for uncovering your past and empowering your future, today announced the publication of an extensive collection of historic U.S. city directories in the works for two years. The collection was produced by MyHeritage from 25,000 public directories of US cities published between 1860 and 1960. It includes 545 million aggregated records that were automatically consolidated from 1.3 billion records. This addition brings the total size of MyHeritage’s historical records database to 11.9 billion records.

The MyHeritage teams have applied innovative technologies to produce this collection and make it as useful and easy to use as possible. The city directories in this collection have been published by cities and towns across the United States, and each directory is formatted differently. To overcome formatting differences and unify structures, MyHeritage fixed errors in optical character recognition of scanned directory pages, then used several advanced technologies, including record extraction, name entity recognition and conditional random fields to analyze the data. By training a machine learning model to parse raw free text records into names, occupations and addresses, the company produced a structured and searchable index of valuable historical information.

As an important resource for family history research, city directories can provide fascinating new discoveries for anyone exploring their family history in America from the mid-19th to the mid-20th century. The files contain valuable information about daily American life spanning the period from the Civil War to the Civil Rights movement. Cities in the United States have been producing and distributing directories since the 1700s, providing an up-to-date resource to help residents find and contact local individuals and businesses. The city directories provide a wealth of information on family life during these years, listing names, residences, occupations and relationships between individuals. With their exceptional level of detail, city directories can also be a viable alternative to U.S. census records in non-census years and can fill gaps in situations where census records have been lost or destroyed. In 1921, a fire in the US Department of Commerce destroyed most of the 1890 census records. Despite the loss of records in the fire, much of the data can be reconstructed using the 1890 city directories on MyHeritage , which consist of directories of 344 cities across the country, including 88 of the 100 most populous cities during this year.

“We are harnessing new technologies to make family history research more accessible than ever before,” said Tal Erlichman, director of product management at MyHeritage. “The use of machine learning to process city directory records highlights the major advancements that MyHeritage has made in digitizing global historical records. ”

MyHeritage has automatically grouped multiple entries for the same individual into a single, robust record that includes data from all years an individual has lived at the same address. This makes it easier to keep track of how life circumstances change over the years. Users can more easily see when their ancestors changed professions or got married, divorced, or widowed – and MyHeritage automatically infers approximate dates for these life events. The inferred dates contribute to a better match between family trees and historical records on MyHeritage.

MyHeritage currently indexes thousands of additional US city directories that will be added to the collection in the coming months. This addition will include directories dating back to the end of the 18th century, as well as a large and unique collection of directories from the end of the 20th century.

The online collection of US city directories is now available on SuperSearch â„¢, MyHeritage’s search engine for historical records. Searching the collection is free. A subscription is required to view full records and access record matches.

Look for the new US City Directories collection.

About MyHeritage

MyHeritage is the world’s leading discovery platform for exploring family history and gaining valuable health information. With billions of historical records and family tree profiles, and with sophisticated matching technologies that work across all of its assets, MyHeritage empowers users to uncover their past and strengthen their future. Launched in 2016, MyHeritage DNA has grown into one of the world’s largest consumer DNA databases, with 3.9 million people. As the world’s first global service that combines family history and DNA testing for genealogy and health, MyHeritage is uniquely positioned to provide users with a meaningful discovery experience that unites their past, present and future. Available in 42 languages, MyHeritage is the most popular DNA and family history testing service in Europe. www.monheritage.com


Comments are closed.