System and method for real-time dynamic measurement of best-estimate quality levels while reviewing classified or enriched data
A system, method and computer program product for validating a document classification process, including a document collection; a document classification process performed on the document collection; a random selection module configured to automatically generate a random validation set of documents from the document collection; and a document review process performed on the random validation set of documents to validate results of the document classification process. The system, method and computer program product are configured to dynamically and in real-time measure and display on a computer display device a best case estimate of a quality of the results of the document classification process based on the documents that are validated, and given a size of a total data set of the document collection.
1. A computer implemented system for validating a document classification process for eDiscovery, internal investigations, law enforcement activities, compliance audits, records management, legacy data clean-up, or defensible dispositions, the system comprising:
a document collection of N documents related to eDiscovery, internal investigations, law enforcement activities, compliance audits, records management, legacy data clean-up, or defensible dispositions;
a document classification process performed on the document collection;
a random selection module configured to automatically generate a random validation set S of documents based on a user selectable percentage P of the N documents from the document collection; and
a manual document review process performed on the random validation set of documents to validate overall results of all of the documents classified by the document classification process,
wherein the system is configured to dynamically and in real-time measure and display on a computer display device a best case estimate of a quality of the results of the overall document classification process based on the documents that are validated, given the size N of a total data set of the document collection, and based on a predetermined quality threshold for an overall classification quality desired for the document classification process.
2. The system of claim 1 , wherein the system is configured to allow a user to monitor the best case estimate of the overall classification quality and terminate the document review process and change parameters and/or instruction for the document classification process based on the best case estimate of the overall classification quality being equal to or lower than the predetermined quality threshold of the documents in the random selected document set.
3. The system of claim 2 , wherein the system is configured to allow the user to accept an original classification of all the documents in the entire document set based on the best case estimate being equal to or higher than the predetermined quality threshold of the documents in the random selected document set.
4. A computer implemented method for validating a document classification process for eDiscovery, internal investigations, law enforcement activities, compliance audits, records management, legacy data clean-up, or defensible dispositions, the method comprising:
providing a document collection of N documents related to eDiscovery, internal investigations, law enforcement activities, compliance audits, records management, legacy data clean-up, or defensible dispositions;
performing a document classification process on the document collection;
automatically generating with a random selection module a random validation set S of documents based on a user selectable percentage P of the N documents from the document collection; and
performing a manual document review process on the random validation set of documents to validate overall results of all of the documents classified by the document classification process; and
dynamically and in real-time measuring and displaying on a computer display device a best case estimate of a quality of the results of the overall document classification process based on the documents that are validated, given the size N of a total data set of the document collection, and based on a predetermined quality threshold for an overall classification quality desired for the document classification process.
5. The method of claim 4 , further comprising allowing a user to monitor the best case estimate of the overall classification quality and terminate the document review process and change parameters and/or instruction for the document classification process based on the best case estimate of the overall classification quality being equal to or lower than the predetermined quality threshold of the documents in the random selected document set.
6. The method of claim 5 , further comprising allowing the user to accept an original classification of all the documents in the entire document set based on the best case estimate being equal to or higher than the predetermined quality threshold of the documents in the random selected document set.
7. A computer program product for validating a document classification process for eDiscovery, internal investigations, law enforcement activities, compliance audits, records management, legacy data clean-up, or defensible dispositions and including one or more computer readable instructions embedded on a tangible, non-transitory computer readable medium and configured to cause one or more computer processors to perform the steps of:
providing a document collection of N documents related to eDiscovery, internal investigations, law enforcement activities, compliance audits, records management, legacy data clean-up, or defensible dispositions;
performing a document classification process on the document collection;
automatically generating with a random selection module a random validation set S of documents based on a user selectable percentage P of the N documents from the document collection; and
performing a manual document review process on the random validation set of documents to validate overall results of all of the documents classified by the document classification process; and
dynamically and in real-time measuring and displaying on a computer display device a best case estimate of a quality of the results of the overall document classification process based on the documents that are validated, given the size N of a total data set of the document collection, and based on a predetermined quality threshold for an overall classification quality desired for the document classification process.
8. The computer program product of claim 4 , further comprising allowing a user to monitor the best case estimate of the overall classification quality and terminate the document review process and change parameters and/or instruction for the document classification process based on the best case estimate of the overall classification quality being equal to or lower than the predetermined quality threshold of the documents in the random selected document set.
9. The computer program product of claim 8 , further comprising allowing the user to accept an original classification of all the documents in the entire document set based on the best case estimate being equal to or higher than the predetermined quality threshold of the documents in the random selected document set.