How Relativity Defines a Number
When you set up a Textual Near Duplicate Identification structured analytics operation in Relativity, you have the option of ignoring numbers. Documents such as spreadsheets with rows and rows of numerical data will not be evaluated on the basis of those numbers with documents that have similar content. Documents which only contain numbers will be excluded from the review set altogether.
When preparing an Analytics Index, the admin can select the option to 'Optimize training set', which among other things will remove documents with long lists of numbers from the training set for the index.
How does Relativity define a number? Relativity will remove words when either the first character is a digit, or the first character is not digit and is followed by a second character that is a digit. So, for example:
1. 90754289076 - REMOVED
2. 786FTC - REMOVED
3. Z4508972 - RETAINED
4. #54879 - REMOVED
6. $878 - REMOVED
7. @$715 - RETAINED
8. A199 - RETAINED