Sign-up today to see an in-depth, click-by-click demo of Feith software and solutions.

Home / Records Management / Auto-Categorizer

Command your categories

There is simply too much data at your organization for manual categorization processes to be efficient. Yet, proper Records Management and Information Governance require that you know exactly what sort of documents you’re dealing with.

Enter Feith’s Auto-Categorizer. Using advanced statistical modeling to read and categorize documents automatically, Auto-Categorizer solves the problem of data overload by leveraging the power of machine learning. Your documents and email, along with their associated metadata, are evaluated, categorized and processed all without human intervention. Welcome to the age of smart machines.

Automation in your hands

Now you can perform sophisticated, automated categorization of the structured and unstructured data in your repositories. Feith learns to make decisions based on a combination of word matching, phrase matching, metadata matching, and knowledge accumulated in a training process for text matching. This learning and decision making functionality makes Feith well-suited to conquering unstructured data repositories, like email, network drives, SharePoint and more.

Feith’s Auto-Categorizer application is a fully-integrated and fully-automated auto-categorization solution arranged in a “waterfall” architecture that ensures both electronic and paper records are acquired and ingested securely and efficiently based on your industrial, organizational, or governmental requirements.

How it works

  • Set up categorization rules
  • Capture documents into archive
  • Categorize on metadata or content
  • Compare docs with training set
  • Apply retention and classifications

Once it’s categorized

Auto-categorizer is smart for you

Feith’s Auto-Categorizer learns to recognize your document category type employing the Bayes Theorem to inform its trainable categorization engine. With adequate training, the engine has the ability to return extremely high percentages of accuracy, putting a large dent in your categorization workload.