Today’s companies are looking for technologies that can help wring value out of unstructured data within a company. Arikus delivers.

Arikus

Plain Language: Arikus employs state of the art linguistic technologies: A sophisticated statistical analysis using concepts from Information Retrieval, Information Theory, Linear Algebra and Machine Learning are used to "understand" the queries and documents that it is processing.

Arikus brings together a company’s external and internal data resources and allows it to use this data on its own terms; automated information management, plain language precision search, and navigation software for self-service applications.

At the basis of any good information management platform is the ability to rank a document against a query. This basic operation allows for all other operations. Without a good ranking algorithm at its core nothing else will work well.

The Competition

Technologies based on the following methods have several limitations:

Keyword Searches: Results are not ranked, leaving the user to differentiate between good & bad articles. It is difficult for users to construct and refine queries.

Popularity Ranking: Keyword search combined with the analysis of a page's prominence against others in a categorical search to determine which is most often referred and linked to — this is less valuable in the structured design of business sites or intranets.

Pattern Matching or Neural Networks: Plagued by the inability to know when training is done. Long articles exhibit multiple patterns and are erroneously returned.

Fuzzy Boolean: Documents are viewed as a “bag of words” resulting in poor discrimination between relevant and non-relevant documents.