Learn More

Broad Spectrum Analytics.  VŌR’s analytics encompass multiple techniques and methods in each form of analytics (descriptive, predictive and prescriptive) because we believe there is no single, right way to view all data.  VŌR automatically competes multiple methods and leverages them cooperatively to provide deep, rich, meaningful insights into data.  By leveraging multiple analytics views of the data, customers get high-quality, high-confidence answers that better support critical business decisions.

Unknown Discovery.  When confronted with large data sets, most approaches automate the simple tasks of describing the data.  However, to gain rich insight in the data and discover unknown relationships, correlations, models, behaviors, and causal triggers most leverage the cognitive power of human analysts, each with their own perspective/bias of the data.  VŌR automates the discovery of unknowns by taking an unbiased, naive approach to exploring data, exposing relationships and behaviors that it finds “interesting” and asking the user which discovery has meaning.  VŌR learns from this relationship discovery and human subject matter expert interaction and can delve further into the data and new discoveries, forming hypotheses about the unknowns and attempting to model these new discoveries so users can better exploit the knowledge VŌR presents them.  The benefit of unknown discovery is the ability to identify hidden, hard to see associations within the holistic data set, which drives a richer knowledge base, driving smarter decisions.

Hypothesis Generation and Exploration.  What makes human analysts more insightful than traditional analytics programs?  The answer lies in humans’ ability to leverage multiple forms of reasoning, learned and experiential knowledge and to develop potential explanations or models that fit the situation. This is done through not only cognitive functions, but also through intuition, emotion and gut feel.  To date, machines have struggled with hypothesis generation as the rules for generating hypotheses are not static and not well-defined by a set of simple heuristics.  ISSAC has developed multiple methods and mechanisms to automatically generate hypotheses from data sets and explore them to understand which potential hypotheses are most likely valid and which have the biggest impact on an organization.  The Unknown Discoveries previously discussed enhance the relationships within the data that further improves the quality of these hypotheses.  The results focus potential courses of action an organization should pursue, with higher levels of confidence, driving the prescriptive outcomes of the future more accurately. The ISSAC developed Hyper Agent Simulation Programs (HASP) tool is leveraged for Hypothesis Generation and Exploration.

Iterative Analytics.  While there is great benefit to providing analysis based-on historical data, most organizations have critical real-time needs that require rich, deep analytics of current information as well.  VŌR provides both historical and real-time analytics with the historical analytics informing and evolving the real-time analysis quality.  Automated orchestration of historical analyses and updating real-time analytics provides an iterative framework to ensure real-time analytics and notifications provided to the user are as well informed as possible.  The result of the Iterative Analytics process is an ever-evolving enrichment of the knowledge available to the customer.  The more the system iterates on historical and real-time information, as well as interaction with subject matter experts, the more confident the hypothesis and courses of action become.