Large Data Collections

Attempting to tackle large data collections that can contain hundreds of gigabytes and millions of documents can be a daunting task for any legal team to face. Inference allows even small teams to quickly navigate through the largest datasets by providing tools such as Concept Clustering and statistical relevancy filters.

Conceptual Analytics for Investigation & Prioritization.
Inference is the first user-driven eDiscovery platform to address the need to quickly and thoroughly analyze entire datasets. With Inference’s suite of conceptual analytic tools, features like Clustering and Show Similar, enable dynamic investigation, acceleration, and prioritization of data to dramatically streamline review. With Inference’s ability to determine document relationships by topic, team members can quickly identify and eliminate irrelevant data sets from being included in future review efforts.  Combined with features such as:

Minimum Similarity Filter.
This feature requires documents in a search to meet “minimum conceptual similarity” requirements to be responsive. By applying a minimum similarity filter, reviewers can expand or broaden their search for important, or irrelevant, data.

Relevance Ranking.
Quickly sorting document sets by relevancy allows top priority documents to be immediately visible to review team members.

Show Similar.
By identifying documents that are conceptually equivalent, Show Similar enables users to find documents around an already identified theme, and quickly bulk tag all documents that share a strong relationship to streamline and prioritize.

De-duplication.
Inference’s advanced De-duplication process ensures that unnecessary copies of documents are removed during the ingestion process, eliminating redundant documents from the review set.

Folders and Collections.
Data sets are comprised of large amounts of information. Inference offers the flexibility to segregate the data into individual sections for ease of management and refinement of searching.