QMiner is a data analytics platform for processing large-scale real-time streams containing structured and unstructured data.
QMiner implements a comprehensive set of techniques for supervised, unsupervised and active learning on streams of data.
QMiner enables easy extraction of rich feature vectors from data streams using the data importing, normalization, re-sampling, merging and enrichment functionality.
QMiner provides support for unstructured data, such as text and social networks across the entire processing pipeline, from feature engineering and indexing to aggregation and machine learning.
QMiner provides out-of-the-box support for indexing, querying and aggregating structured, unstructured and geospatial data using a simple query language.
QMiner is implemented in C++ and can be included as a library into custom C++ projects, thus providing them with stream processing and data analytics capabilities.
The Event Registry is a system that can automatically identify events happening across the world that have been reported in news articles. For each event it can extract, from the available articles, the main information about the event (who, when, where, …).
AI Lab, Jozef Stefan Institute
QMiner powers a state-of-the-art recommendation system, which provides accurate and up-to-date recommendations for highly dynamic domains. Examples of such domains include news portals, IPTV and social media.
QMiner is developed in collaboration between AILab at Jozef Stefan Institute and Quintelligence. The development was started by Blaz Fortuna and is now headed together with Jan Rupnik.
The following people provided significant contribution to the development of QMiner (in alphabetic order): Janez Brank, Carolina Fortuna, Marko Grobelnik, Viktor Jovanoski, Mario Karlovcec, Blaz Kazic, Klemen Kenda, Gregor Leban, Dunja Mladenic, Andrej Muhic, Blaz Novak, Erik Novak, Jost Novljan, Miha Papler, Luis Rei, Blaz Sovdat, Luka Stopar.