Contact Us Now
Known Networks® continues to be improved by our Data Science staff using cutting edge machine learning tools, leading to meaningful improvements in value. In March 2017 alone, we provided an increase in coverage (address space) of 14% – that’s approximately 240M of IP address space added, employing methods we expect to continue to yield further improvements. We collect megabytes of data every day about what is knowable regarding network characteristics – all of which requires extensive cleaning and cross-correlation.
Our Data Science staff use data science workbench systems that include, each of which has played a part in the research resulting in the current Known Networks® product:
- The R programming language and software environment for statistical computing.
- The Scikit-learn machine learning library for Python. Both Scikit-learn and R have libraries for common classification, regression, and clustering algorithms including logistic regression, linear regression, support vector machines, random forests, gradient boosting, k-means, and neural networks.
- The SciPy scientific computing library for Python.
- The NumPy numerical and array computing library for Python.
- The Natural Language Toolkit (NLTK) suite of libraries for symbolic and statistical natural language processing (NLP) for Python.
Release 2 Innovations created the Known Networks® data product after realizing that there was a real need for their customers, both government and commercial, to accurately identify and characterize networks within the context of the entire internet.
Known Networks® enables powerful filtering not otherwise possible by combining your existing cyber data with relevant and timely enriched data.