UNICO Research Laboratory (UnicoLab)

The laboratory is operated in cooperation with the UNICO company. We offer students the opportunity to get involved in the company’s research activities and solve practical tasks in the field of big data integration and mining. UNICO’s main activity is connecting academia with industry using artificial intelligence tools and consulting services. We build unique systems that fundamentally improve the functioning of the entire ecosystem, such as EXPERTS.AI.

More about the company

What we do

We want cooperation between companies and universities to be transparent and beneficial for both parties. We help them work smarter together by processing big data and using unique artificial intelligence. Our goal is to show both parties a unified and simple way of cooperation that will effectively connect the offer of universities with the demand of companies.

We have data on experts, patents and innovations from several countries. Various algorithms can be created (researched) over the data, from automatic data cleansing to network algorithms or recommender systems.

In particular, we focus on processing big data from public sources. We use data mining algorithms and best practices from the data warehouses for advanced data cleansing. We use the data to develop recommender systems based on ontologies and other approaches. We conduct research at both theoretical and practical levels. We strive to translate research results directly into practice.

Search our experts, research outcomes and industrial projects

The widget is operated by UNICO.


Reducing Cold Start Problems in Educational Recommender Systems

2016 International Joint Conference on Neural Networks (IJCNN). San Francisco: American Institute of Physics and Magnetic Society of the IEEE, 2016. p. 3143-3149. ISSN 2161-4407. ISBN 978-1-5090-0620-5.
Proceedings paper
Educational data can help us to personalise university information systems. In this paper, we show how educational data can be used to improve the performance of interaction-based recommender systems. Educational data is transformed to student profiles helping to prevent cold start problems when recommending projects to students with few user interactions. Our results show that our hybrid interaction based recommender boosted by educational profiles significantly outperforms bestseller recommendation, which is a mainstream recommendation method for cold start users.

Mining skills from educational data for project recommendations

Proceedings of the International Joint Conference CISIS’15 and ICEUTE’15. Berlin: Springer-Verlag, 2015, pp. 617-627. Advances in Intelligent Systems and Computing. ISSN 2194-5357. ISBN 978-3-319-19713-5.
Proceedings paper
We are focusing on an issue regarding how to actually recognize the skills of students based on educational results. Existing approaches do not offer suitable solutions. This paper will introduce algorithms making possible to aggregate educational results using ontology. We map the aggregated results, using various methods, as skills that are understandable for external partners and usable to recommend students for projects and projects for students. We compare the results of individual algorithms with subjective assessments of students, and we apply a recommendation algorithm that closely models these skills.

A tour of the lab

Contact person

Ing. Stanislav Kuznetsov, Ph.D.

Where to find us

UNICO Research Laboratory
Department of Applied Mathematics
Faculty of Information Technology
Czech Technical University in Prague

Room TH:A-1347 (Building A, 13th floor)
Thákurova 7
Prague 6 – Dejvice
160 00

The person responsible for the content of this page: doc. Ing. Štěpán Starosta, Ph.D.