Black Oak Analytics, Inc.
Seamlessly Connecting Disparate Datasets

The amount of data available today is staggering. To manage the sheer volume of information, it is essential for enterprises to have entity resolution at workplace. Effective entity resolution software allows businesses to gain better insights of their products and customers, significantly growing their market share. The Little Rock, AR based firm, Black Oak Analytics’ flagship product, High Performance Entity Resolution (HiPER), organizes these disparate data points by linking them together to provide data clarity and combat data duplication. “By matching information across scattered databases, we can identity non-obvious connections between individuals, helping customers make better business decisions,” says Robert Nosari, Director of Product Development at Black Oak. “The primary use case for HiPER is entity resolution, which revolves around identity resolution, identity management, record linkage, and deduplication,” adds Dr. John R Talburt, Chief Science Officer, Black Oak.

Existing data integration software in companies today typically has rigid match rules, designed to match on a handful of possible structured data attributes. However, when combined with Black Oak’s HiPER, companies can design customized match rules for incoming structured and unstructured data. “We have engineered HiPER to run in the Hadoop distribution file system environment,” says Talburt. This next-generation advanced entity resolution software enables clients to create actionable, comprehensive views of data with unparallel speed and scalability, even in the absence of Personally Identifiable Information (PII). Leveraging HiPER, clients can easily pre-process all their records flowing into data warehouses. “Customers can have an accurate and complete view of each entity’s information, regardless of the point of entry, subsystem capturing the information, or time of encounter,” states Nosari.

With its customizable algorithms, HiPER can also indicate when the records are incorrectly linked or unlinked.Subsequently, it produces an exception report to support review and correction by domain experts to ensure a high level of accuracy and compliance. Beyond just managing entity resolution, Black Oak also provides a DataDriven Marketing solution that follows a systematic approach to collect, consolidate, and process consumer or enterprise data— enabling companies to communicate with their current and potential customers.

The primary use case for HiPER is entity resolution, which revolves around identity resolution, identity management, record linkage, and deduplication

DataDriven Marketing can be deployed anywhere, empowering clients to run the entity resolution engine behind the firewall.

“To further help clients improve their metadata management, we also provide analytics consulting services around data governance and master data management focused on client specific analytics projects and model development,” says Warren Smith, Principal Architect, Black Oak. These engagements, focused at enhancing client specific analytics projects and model development, helps clients gather information around data governance needs and recommendations, and accordingly provide solutions.

In one instance of working with a healthcare institution, Black Oak discovered that the client was receiving health records from over 25 hospitals in the region and failed to manage the information effectively. Integrating records from several different hospitals, the healthcare firm faced issues in managing the identities, often resulting in duplication. “With HiPER, we were able to get their error rates down to less than one percent, giving them an accurate clinical review of the results,” extols Smith.

As businesses shift their existing infrastructures into the Hadoop distributed processing environment, CIOs are experiencing cut-throat challenges around master data management and data governance. Looking forward to combating these big data problems, Black Oak is laying their foundation to enter into the realm of machine learning, turning the big data space into an ‘algorithmic economy.’