Apr. 12, 2011 (GlobeNewswire) --
CHICAGO, April 12, 2011 (GLOBE NEWSWIRE) -- Salford Systems returns to the 11th annual Institute for Operations Research and the Management Sciences Conference where one of its clients received first runner-up at the 2009 conference for a health care quality application. Today senior scientist Mikhail Golovnya will present data mining technology to commercial users in a user-friendly approach at the conference's technology workshop.
No longer is data mining reserved exclusively for scientists, but modelers in every-day work environments can extract valuable, business-enhancing information as well. Salford's advanced technology, important for predicting future trends and behaviors, is intended for the modeler interested in real-world applications for data analysis such as banking, education, defense, financial services, health care, insurance, manufacturing, marketing, retail, sports, telecommunications, etc.
"Salford's data mining software is extremely user-friendly and with minimal training, which we offer, any business can apply them to their own datasets" said Golovnya. "Data mining tools can answer business questions that traditionally were too time consuming to resolve." With the training that Salford Systems offers to its clients, the software can be applied to explore datasets for hidden patterns, ultimately finding predictive information that some experts may miss if it is not within their initial expectations.
Golovnya will spend his 50-minute tutorial discussing the main concepts behind three of Salford Systems' well-known algorithms: CART®, MARS® and TreeNet®. Additionally, the workshop will use illustrative real-world examples; and, discuss cover implementation and deployment.
CART® (Classification and Regression Trees). Noted for its modeling accuracy, performance, visualization, feature set automation and ease of use, CART analyzes large and complex databases to generate classification and regression trees that quickly reveal important data patterns and relationships that could remain hidden using other analytical tools.
MARS® (Multivariate Adaptive Regression Splines). Ideal for users who prefer results in a form similar to traditional regression while capturing essential nonlinearities and interactions. Its flexibility permits MARS to trace out non-linear patterns detected in the data. It can predict continuous numeric outcomes as well as probability models for yes/no outcomes.
TreeNet®. TreeNet is the proprietary technology underlying major recent advances in fraud detection, targeted marketing, and risk modeling.