January 30, 2014
By DE Editors
KnowledgeMiner Software announced the release and immediate availability of Insights 3.0 for Mac OS X, an update to the company’s self-organizing, predictive modeling application. With Similar Patterns technology Insights 3.0 adds forecasting to its adaptively learning modeling methods. Insights is used for predicting sales, production and demand, engineering problems, climate change, health or life sciences-related questions, or mining collections of data from government agencies.
The 64-bit parallel software also hides all complex processes (such as knowledge extraction) from the user, and self-organizes data and models, as well as generalizes the equation that describes the data. It includes live prediction validation technology, and can implement models and model ensembles in Microsoft Excel.
Insights has AI-powered modeling algorithms that allow users to extract new knowledge to support decision-making, the company says. Users can develop predictive models and model ensembles, along with a prediction interval from low to high-dimensional noisy data, of up to several hundreds of input variables.
According to the company: “Since complex, fuzzy, or very noisy processes are hard to model and predict by known parametric modeling and data mining technologies, Insights features Similar Patterns self-organizing technology. Similar Patterns can be seen as a sequential pattern recognition method that predicts and qualitatively explains fuzzy processes inherently. This method is based on the assumption that every most recent period of time (reference pattern) of a given multi-dimensional time process has one or more analogous periods in history (similar patterns). If so, a forecast of the reference pattern can be obtained by transforming the known continuations of the similar patterns in history into continuations of the present state of the process. This means the observed process itself is used to forecast its most recent state by a nonparametric approach.”
“Insights opens up a wealth of new possibilities to individuals, small business owners and scientists that were previously available only to large entities that could afford expensive data mining application,” said Frank Lemke, founder of KnowledgeMiner Software. “The ability to continuously make predictions from auto-associative past patterns is the core of human intelligence. Self-similarity is a phenomenon often found in nature such as the Golden Ratio. Our Similar Patterns technology now make these proven and powerful concepts available for solving forecasting problems in many fields.”
For more information, visit KnowledgeMiner Software.
Sources: Press materials received from the company and additional information gleaned from the company’s website.