In a high profiled international bankruptcy case, lawyers turned to e-discovery to uncover foul play. Lawyers had to provide proof from emails and documents that key executives were aware of the fragile financial situation leading up to bankruptcy while assets were transferred to another company, leaving creditors potentially facing multimillion dollar losses. In the aftermath of the trial, the accusers law firm would carry out a benchmark of the traditional e-discovery’s results against Anzyz’ hybrid-AI system.
While traditional e-discoveries rely on human annotators manually labeling the data, Anzyz’ AI is fed large amounts of unstructured data and must find patterns and relationships on its own. In other words, the system learns from data without human intervention, thus removing the mundane work of having to manually train the AI, resulting in faster and more accurate reviews for legal professionals.
The dataset, consisting of thousands of emails and documents, was automatically modelled by the Anzyz’ CCL™ algorithm. When the AI-model had been created, the lawyers were immediately able to query the knowledge base by introducing voluntary terms into a concept-based search system, essentially a precision layer of deterministic rules for fine-grained control. Besides allowing the user to tag narrative text with similar accuracy as traditional systems, this layer also helps with interpretability and to correct errors reported by end users.
In summary, Anzyz’ hybrid-AI system gave insights previously not detected by the traditional e-discovery system. The AI-model was deployed in a matter of hours, compared to otherwise manual labeling processes stretching for several days. At the same time the user-friendliness was reported to be high, with human-in-the-loop capabilities further enhancing user-experience, accuracy, and transparency of results, where the underlying interpretations can be traced back to the original raw data.