University
Community
International Students
Studies
Research and Innovation
For Business
Faculties
Back

VILNIUS TECH Business Management Faculty graduate – laureate of a prestigious competition

December 11, 2024
We are pleased to announce that Paulina Mikuciauskaite, a graduate of the Finance Engineering Department at the VILNIUS TECH Business Management Faculty, has been awarded in the "Best Master's Thesis 2024" competition in the field of social sciences. Paulina's master's thesis, "Securities research using deep learning and portfolio optimization," was recognized as outstanding in the competition organized by the Lithuanian Young Scientists' Union. The thesis was supervised by Associate Professor Dr. Nijole Maknickiene from the Finance Engineering Department.

We spoke with Paulina and her thesis supervisor about the award, the research process, and the formula for success.

Paulina's success brings joy not only to herself but also to her thesis supervisor, Associate Professor Dr. Nijole Maknickiene. According to the supervisor, this award proves that hard work, innovative solutions, and perseverance can lead to exceptional results. She proudly shares her insights on what led to such a high evaluation of the work as well as the success formula.

– Why do you think this thesis was recognized in the competition?

The thesis is very consistent. The foundation is based on a classical idea, but the methods are innovative and logically structured. The MCDM method was used to rank stocks, the LSTM algorithm was applied for price forecasting, and the Black-Litterman optimization algorithm was used to create portfolios that were tested in real-time. This synergy was unique.

– What was the basis for preparing a successful thesis?

It was the synergy between the student, the university, and the supervisor. The university provided access to MATLAB software and research publications. Paulina stood out for her perfectionism and persistence. Although the thesis was nearly completed, she conducted additional research in the final weeks, which helped achieve excellent results.

Paulina Mikuciauskaite's journey to the prestigious award is a story of courage in tackling complex topics, a passion for science, and consistent work. Choosing to explore stock market forecasting and portfolio optimization using deep learning, Paulina not only overcame academic challenges but also developed a practical decision support system for investors. She shares her insights, results, and advice that can inspire other students to aim for the highest goals.

– Why did you choose this topic, and why is it relevant?

I chose this topic because it was one of the most interesting yet challenging subject matters. I am intrigued by the investment field, especially the difficulty of forecasting the stock market. Deep learning is currently a modern tool, and its application to portfolio optimization seemed interesting as a new challenge.

– What were the main results of your research?

I managed to create a system for investors that combines several methods. We defined investment parameters, narrowed down stock choices using MCDM, forecasted prices with the LSTM algorithm, and applied the Markowitz as well as Black-Litterman methods for portfolio optimization. The system helps not only to select but also to evaluate the best strategies.

– What is the recipe for success when writing a master’s thesis?

It is important to balance work and rest, but the thesis must be a priority. I aimed for perfection and persistently searched for solutions even when difficulties arose. It is also crucial to accept insights and constructive criticism from the supervisor and professors.

– What advice would you give to other students?

Paulina's success not only inspires but also demonstrates how modern scientific methods can be applied in practice. We congratulate Paulina and wish her many more professional and academic victories!

We would like to thank the thesis supervisor, Associate Professor Dr. Nijole Maknickiene, and Business Management Faculty alumna Paulina Mikuciauskaite for their excellent results and the warm conversation. We are proud of our community!

The interview was prepared by Dr. Jolanta Nalivaike, Vice Dean for Communication and Community at the VILNIUS TECH Business Management Faculty.

Galerija

Related news

New doctoral dissertation
New doctoral dissertation
VILNIUS TECH Library invites you to follow the published new dissertations. The dissertation „Research and application of machine learning methods for migraine attack prediction“ prepared at VILNIUS TECH by Viroslava Kapustynska. The dissertation was prepared in 2021–2026. Scientific consultant – Prof. Dr Šarūnas Paulikas. The dissertation was defended at the public meeting of the Dissertation Defense Council of the Scientific Field of Electrical and Electronic Engineering in the Aula Doctoralis Meeting Hall of Vilnius Gediminas Technical University at 2 p.m. on 9 June 2026. Migraine is a complex neurological disorder characterized by strong inter- and intra-individual variability, which makes early forecasting difficult using only clinical observations. Wearable biosensors combined with machine learning offer new opportunities to detect subtle physiological changes that may precede migraine attacks and to develop individualized prediction models. This dissertation investigates migraine analysis and next-day prediction using physiological recordings collected under real-life monitoring conditions. Data were obtained with the Empatica Embrace Plus wearable device and include electrodermal activity, pulse rate, skin temperature, and movement-related signals. The analysis focuses on nocturnal recordings, since the night period provides a more stable physiological context with fewer external disturbances. Nights were standardized using sleep-based contextual selection and consistent night-level rules. The experimental framework is organized in two stages. In the first stage, a window-level binary classification task is used as an exploratory methodological analysis to examine how design choices influence model performance. Night recordings are segmented into analysis frames ranging from 5 to 120 minutes, statistical features are extracted, and the influence of signal preprocessing and feature representation is evaluated across several classifier families, including Random Forest, XGBoost, histogram-based gradient boosting, support vector machines, and k-nearest neighbors. In the second stage, the research evaluates next-day migraine prediction based on whole-night recordings. This stage refines the experimental methodology to obtain more reliable estimates of predictive performance under a stricter validation framework. The analysis focuses on the effect of temporal aggregation while comparing the same classifier families under consistent evaluation conditions. The results demonstrate considerable variability across participants in achievable prediction performance and optimal modeling configurations. Shorter analysis frames generally preserve informative short-term physiological changes, whereas longer windows tend to smooth these variations. Signal preprocessing shows a window-dependent effect and does not consistently improve performance. Overall, the results highlight the importance of temporal resolution, rigorous validation, and individualized modeling for wearable-based migraine prediction systems. Doctoral dissertation readers can search via VILNIUS TECH Virtual Library.
More
Expert Evaluation: VILNIUS TECH’s Progress Exceeded Expectations
Expert Evaluation: VILNIUS TECH’s Progress Exceeded Expectations
VILNIUS TECH has received a highly positive assessment from international experts. In their recently published conclusions, it is noted that since the 2022 institutional evaluation, the university has achieved significant, evidence-based progress across all four evaluation areas: governance, quality assurance, studies and research activities, and impact on regional and national development. In 2022, VILNIUS TECH was granted a seven-year accreditation. At that time, the expert panel provided the university with 19 recommendations for further improvement. The latest progress review concludes that the university responded to these recommendations responsibly, systematically, and constructively, and that the implemented changes have become part of long-term institutional development. „We are pleased that external experts have highly evaluated the progress achieved by VILNIUS TECH across all four assessment areas. It was noted that the university demonstrates a mature quality culture, a strategic vision, and the ability to consistently sustain growth and increase its impact on society. This ensures that we are entering the next institutional evaluation period with a strong position,“ says Nora Skaburskienė, Director of the Studies Directorate. International experts particularly highlighted the consistently strengthened system of strategic management, the quality culture, active collaboration with business and alumni, leadership within the ATHENA European Universities Alliance, the development of new interdisciplinary study programmes, and significant progress in innovation and technology transfer. The rapid expansion of lifelong learning activities was also noted — VILNIUS TECH has broadened its micro-credential offerings, strengthened partnerships with social and business partners, and is creating favourable conditions for knowledge commercialization and startup development. According to the expert panel, the university has already moved beyond the stage of merely responding to recommendations and is now ready to purposefully leverage its accumulated potential to achieve even higher performance results. In summarizing the evaluation, the experts concluded that VILNIUS TECH is entering the next phase of institutional assessment with a solid foundation for continued successful development.
More