Insights: Software that extracts knowledge from data. Model. Predict. Simulate. Discover. Associate. Gain new Knowledge and Insights from noisy data. Easily and Reliably. Ultra-fast, parallel, self-organizing, high-dimensional modeling of real-world processes and complex systems. INSIGHTS
Press Release
September 14, 2017
Innovative Software for Regional and National Macroeconomic Forecasting

Berlin, Germany - KnowledgeMiner Software is pleased to announce the release of INSIGHTS 6 for macOS, a groundbreaking modeling and predictive analytics tool to forecast macroeconomic development in a powerful, new way. It is a major update to its critically acclaimed application that implements original self-organizing modeling technologies based on GMDH Deep Learning for forecasting complex problems in order to provide decision support. INSIGHTS 6 introduces Systems of Equations, a superset of Vector Auto-regressive Models, to allow model development from observation data of linear and non-linear interdependent systems and processes for easy multi-step ex ante forecasting. Accompanying examples such as forecasting the U.S., Japanese, or German national economies until 2021, compared to forecasts provided by the International Monetary Fund, demonstrate the power and productivity of this outstanding modeling technology.

Following the principle of Occam's razor the app autonomously develops complexity-minimized predictive models from observation data and generates new knowledge in form of explicit, dynamic regression model equations that describe the data for further analysis, interpretation and theory formulation purposes. INSIGHTS extracts all information needed for model development from observation data, which is why it is increasingly recognized as a superior alternative and supplemental tool to established domain knowledge-based modeling approaches.

Feature Highlights:

  • Original, high-dimensional, self-organizing, inductive knowledge mining from observation data based on GMDH Deep Learning
  • Systems of Equations for model development of linear and non-linear interdependent systems and processes for easy multi-step ex ante forecasting
  • Automatically develops analytical models and model ensembles from data along with explicit mathematical equations that describe the data as an interpretation of how the model works
  • Integrates all complex tasks - such as relevant variables selection from up to 25,000 inputs, knowledge extraction, model development and validation - into one process that hides it from the user
  • Cost-optimized, prevalence-sensitive classification and sequential Similar Patterns technologies
  • Model deployment and export to Microsoft Excel, ready-to-use Python, Objective-C, AppleScript source code, or TEXT to be used in Matlab
  • Powered by 64-bit, parallel, cross-platform, self-organizing modeling engine for multi-core CPUs

"INSIGHTS data mining and self-specifying model capabilities help us develop more robust and useful tools for ourselves and our clients," says Dr. Randall Pozdena from ECONorthwest, a Pacific Northwest-based economics and finance consultancy. "We have built regional and national macroeconomic models, securities trading tools, event study approaches, and microeconomic market characterizations. Specifically, INSIGHTS is at its most useful when the natural systems are complex and the a priori structure of the equations are unknown. In such settings INSIGHTS data mining and self-organizing capabilities are extremely helpful."

INSIGHTS is applied by corporations, consultancies, universities, research institutes and individuals worldwide for health and life sciences related problems, energy forecasts, sales prediction, economic and financial forecasting and planning, engineering problems, climate change modeling and many more.

Language Support:

  • English, Spanish, and German

System Requirements:

  • OS X 10.9 or later
  • Any Mac with 64-bit CPU, 8+ GB RAM recommended
  • Minimum screen resolution of 1400 x 800 pixel

Pricing and Availability:

INSIGHTS for macOS is available as either Free, Student, Advanced, Professional, or Ultimate edition exclusively from the KnowledgeMiner Software website. Academic versions can be purchased by contacting KnowledgeMiner Software directly. Review copies are available on request. Review copies are available on request.

Located in Berlin, Germany, KnowledgeMiner Software is a privately held company founded in 1993. The company is active in research, development, consulting, and application of outstanding self-organizing modeling and analysis technologies. It developed the distinguished Insights and Ockham tools for the Mac by implementing a number of original technologies for high-dimensional inductive modeling and global sensitivity analysis. KMS has been doing consulting in model development and prediction of toxicological and eco-toxicological hazards and risks of chemical compounds from experimental data for regulatory purposes within REACH and participated in three international research projects funded by the European Commission related to QSAR. Other fields of activity have been climate change related modeling and prediction problems, probabilistic energy forecasting, sales and demand predictions, medical diagnosis, and wastewater reuse problems. Copyright (C) 2017 KnowledgeMiner Software. All Rights Reserved.

More Information:


Deep Learning and noise immunity of GMDH adaptive self-learning and self-organizing data mining, forecasting and classification of streams of data