Ing. Stanislav Kuznetsov, Ph.D.

Publications

Overcoming the Cold-Start Problem in Recommendation Systems with Ontologies and Knowledge Graphs

Year
2023
Published
Communications in Computer and Information Science. 2023, 2023(1850), 591-603. ISSN 1865-0929.
Type
Article
Annotation
Many recommendation systems struggle with the cold-start problem, especially in the early stages of a new application, when there are few active users and limited interactions. Traditional approaches like Collaborative Filtering cannot provide enough recommendations, and text-based methods, while helpful, do not offer sufficient context. This paper argues against the idea that the cold-start phase will eventually disappear and proposes a solution to enhance recommendation performance from the start. We propose using Ontologies and Knowledge Graphs to add a semantic layer to text-based methods and improve the recommendation performance in cold-start scenarios. Our approach uses ontologies to generate a knowledge graph that captures item text attributes’ implicit and explicit characteristics, extending the item profile with similar semantic keywords. We evaluate our method against state-of-the-art text feature extraction techniques and present the results of our experiments.

Personalised Recommendations and Profile Based Re-ranking Improve Distribution of Student Opportunities

Authors
Year
2023
Published
Lecture Notes in Networks and Systems. 2023, 2023(748), 217-227. ISSN 2367-3370.
Type
Article
Annotation
Modern technical universities help students get practical experience. They educate thousands of students and it is hard for them to connect individual students with relevant industry experts and opportunities. This article aims to solve this problem by designing a matchmaking procedure powered by a recommendation system, an ontology, and knowledge graphs. We suggest improving recommendations and reducing the cold-start problem with a re-ranking module based on student educational profiles for students who opt-in. Each student profile is represented as a knowledge graph derived from the successfully completed courses of the individual. The system was tested in an online experiment and demonstrated that recommendations based on student educational profiles and their interaction history significantly improve conversion rates over non-personalised offers.

Offline evaluation of the serendipity in recommendation systems

Authors
Year
2022
Published
IEEE 17th International Conference on Computer Science and Information Technologies. Dortmund: IEEE, 2022. p. 597-601. ISBN 979-8-3503-3431-9.
Type
Proceedings paper
Annotation
Offline optimization of recommender systems is a difficult task. Popular optimization criteria such as RMSE, Recall, and NDCG do not correlate much with online performance, especially when the recommendation algorithm is largely different from the one used to generate the offline data. An exciting direction of research to mitigate this problem is to use more robust optimization criteria. Serendipity is reported to be a promising proxy. However, more variants exist, and it is unclear whether they can be used as a single criterion to optimize. This paper analyzes how serendipity relates to other optimization criteria for three different recommendation algorithms. Based on our findings, we propose to modify the way serendipity is computed. We conduct experiments using three collaborative filtering algorithms: K-Nearest Neighbors, Matrix Factorization, and Embarrassingly Shallow Autoencoder (EASE). We also employ and evaluate the ensemble learning approach and analyze the importance of the individual components of serendipity.

Reducing Cold Start Problems in Educational Recommender Systems

Year
2016
Published
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.
Type
Proceedings paper
Annotation
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

Year
2015
Published
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.
Type
Proceedings paper
Annotation
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.

Utilizing educational data in collaboration with industry

Year
2014
Published
Proceedings of the 13th Annual Conference Znalosti 2014. Praha: VŠE, 2014, pp. 38-47. ISBN 978-80-245-2054-4. Available from: http://znalosti.eu/images/accepted_papers/znalosti2014_paper23.pdf
Type
Proceedings paper
Annotation
Universities are seldom using their data efficiently. In this case study, we show how educational data can be used to recommend suitable students for project, get feedback from industrial partners, help students to focus on skills that are demanded by companies. We have developed portal for students collaboration with industrial partners and run it in a pilot for almost a year. Based on our observations described in this contribution, we are adjusting the portal to enhance the functionality and streamline processes supported by the portal.