10ο κύκλο του Προγράμματος Επιχειρηματικής Επιτάχυνσης «Αρχιμήδης»
Η Μονάδα Μεταφοράς Τεχνολογίας και Καινοτομίας «Αρχιμήδης», καλεί τους φοιτητές και ερευνητές του ΕΚΠΑ που ενδιαφέρονται να αναπτύξουν ή να εξελίξουν μία επιχειρηματική ιδέα, να υποβάλλουν Αίτηση για τη συμμετοχή τους στο 10ο κύκλο του Προγράμματος Επιχειρηματικής Επιτάχυνσης.
Μέσα από διαδραστικά εκπαιδευτικά εργαστήρια, coaching και mentoring από έμπειρους ανθρώπους της αγοράς και με την υποστήριξη ενός ενεργού δικτύου συνεργατών και επιχειρήσεων, το Πρόγραμμα δίνει τη δυνατότητα στα μέλη της Πανεπιστημιακής κοινότητας του ΕΚΠΑ να επεξεργαστούν τις επιχειρηματικές τους ιδέες, να δημιουργήσουν το MVP τους και να λάβουν ανατροφοδότηση, να προσδιορίσουν και να διερευνήσουν την αγορά στην οποία απευθύνονται και να αναζητήσουν ευκαιρίες χρηματοδότησης.
Λεπτομέρειες για το Πρόγραμμα Επιχειρηματικής Επιτάχυνσης, τις υπηρεσίες που προσφέρονται στους συμμετέχοντες, καθώς και η Αίτηση Συμμετοχής, είναι διαθέσιμα στο: https://archimedes.uoa.gr/accelerator–invitation/
MSc Thesis presentation of Mr. Konstantinos Panoutsakos, Monday, October 27, 2025
On Monday, October 27, 2025, at 16:00, Mr. Konstantinos Panoutsakos of the
postgraduate program “Data Science and Information Technologies”, track on “Big Data and Artificial Intelligence”, will present his MSc thesis
titled:
“From Audit Opinion Analysis to Stock Market Signals: Bankruptcy Prediction and Short Selling Strategies”
Abstract
This thesis examines the potential predictive value of audit opinions for forecasting corporate bankruptcy and subsequent stock price movements within the U.S. market. Most prior work on bankruptcy prediction relies on comprehensive financial disclosures (such as Item 10 filings) or combines these with audit opinion data. This research takes a distinct approach, isolating audit opinions as the sole predictive source due to their ready accessibility, interpretability, and computational efficiency for constrained modeling environments.
The study constructed its working dataset from a subset of the ECL data, focusing on U.S. stocks from 1998 to 2021. Critically, each stock required both an available audit opinion and a verifiable bankruptcy outcome (specifically, whether bankruptcy occurred within one year of the opinion’s issuance).
To address the severe class imbalance—where bankruptcies constituted less than 1% of the original sample—the minority class was augmented using lightweight large language models (LLMs), each having fewer than eight billion parameters. This technique effectively expanded the data, rebalancing the class distribution to approximately 86%–14%, thereby providing a more stable foundation for model training. Four machine learning models were then created: three stacked ensemble classifiers and a logistic regression baseline.
Moving beyond traditional bankruptcy forecasting, the resulting probabilities were employed as trading signals to initiate short positions immediately following the release of an audit opinion Interestingly, the model with the weakest F1 score for bankruptcy prediction produced the highest trading returns. This key finding suggests that audit opinions indicating significant financial uncertainty—even in cases that do not result in formal bankruptcy—can precede substantial declines in stock performance.
In sum, this research connects financial auditing, natural language processing, and quantitative finance, indicating that audit opinions, when processed via lightweight LLM-assisted augmentation and classical ensemble learning, may offer valuable predictive insights for both bankruptcy forecasting and anticipating adverse stock price movements.
EXAMINATION COMMITTEE:
Dr Perantonis Stavros, Head of CIL Lab, Institute of Informatics & Telecommunications (IIT), National Centre for Scientific Research “Demokritos”
Dr Zavitsanos Ilias, Research Scientist (C), National Centre for Scientific Research “Demokritos”
Assistant Prof. Panagiotis Stamatopoulos, Department of Informatics and Telecommunications of the University of Athens
Topic: DSIT: Master’s Thesis Presentation, Konstantinos Panoutsakos
Time: Oct 27, 2025 04:00 PM Athens
Join Zoom Meeting
https://us06web.zoom.us/j/81131108334?pwd=1UcoAO6e3AOsr7EjDtXsmFKLlrpEAm.1
Meeting ID: 811 3110 8334
Passcode: 382966
MSc Thesis presentation of Ms. Maria Chasapia, Wednesday, October 22, 2025
On Wednesday, October 22, 2025, at 11:00, Ms. Maria Chasapia of the postgraduate program “Data Science and Information Technologies”, track on “Bioinformatics – Biomedical Data Science”, will present her MSc thesis titled:
Analysis of Rhizosphere at a protein family level through global metagenomics
The plant root microbiome plays a vital role in plant health, nutrient uptake, and environmental resilience. Over millions of years, plants and microbes have developed various associations ranging from mutualistic to parasitic. Plants and their associated microbes can be considered holobionts, in which the host relies on its microbiome for specific functions and traits. To explore and harness this diversity, this thesis presents metagRoot, a specialized and enriched database, that is focused on the protein families of the plant root microbiome. This database holds a massive collection of over 71,000 protein families, each one of them containing at least 100 sequences. This resource was created by integrating data from 1,199 metagenomic studies, 327 metatranscriptomic datasets, and 2,978 reference genomes. The families are annotated with multiple sequence alignments, CRISPR elements, Hidden Markov Models, taxonomic and functional classifications, ecosystem and geolocation metadata, and predicted 3D structures using AlphaFold2. MetagRoot is a powerful tool for decoding the molecular landscape of root-associated microbial communities and advancing microbiome-informed agricultural practices by enriching protein family information with ecological and structural context.
Georgios A. Pavlopoulos, Research Director, IFBR – BSRC Alexander Fleming
Dimitrios J. Stravopodis, Associate Professor, Department of Biology, NKUA
Ioannis Z. Emiris, President & Director General, Athena Research Center & Professor, Department of Informatics and Telecommunications, National and Kapodistrian University of Athens.22 October 2025
11:00 – 12:00 (GTB)
Join Zoom Meeting
https://us05web.zoom.us/j/83982941566?pwd=uMkHSlPaIvgsDyhhTqI3R3f0uEVA1b.1
Meeting ID: 839 8294 1566
Passcode: hh4smK
MSc Thesis presentation of Mr. Kostas Mparmparousis, Wednesday, October 22, 2025
On Wednesday, October 22, 2025, at 14:00, Mr. Kostas Mparmparousis of the
postgraduate program “Data Science and Information Technologies”, track on
“Big Data and Artificial Intelligence”, will present his MSc thesis
titled: “What Drives Learned Optimizer Performance? A Systematic
Evaluation”
Abstract
Classic query optimization is a well-defined and supremely intelligent
process, a cornerstone of database management systems, infused with
decades of empirical knowledge and ingenuity. As traditional optimizers
inevitably begin to pay the toll the (few but impactful) limitations in
their design induce in this modern age of data processing, a new breed of
Learned Query Optimizers (LQOs) promises to surpass those shortcomings and
revolutionize the query execution landscape. Whilst research on this field
continues to flourish, a framework that places such systems under a
microscope and dissects them becomes the top priority, so that the
research community is informed on which factors drive their performance
and how to realize their immense potential.
In this thesis, we propose a systematic framework centered around five
core evaluation dimensions: performance, robustness, learning procedure,
internal decision-making and generalization. Afterwards we leverage said
framework in order to contrast the classic optimizer’s performance against
five of the most prominent LQO implementations. Our findings show that a)
in terms of outright performance the LQOs find the largest windows of
opportunity in settings where the classic optimizer is destined to fail,
b) regression-based LQOs are extremely sensitive to different workload
orders and maximize their effectiveness when exposed to a ascending
complexity curriculum, c) how training progress is tracked has an
immediate effect on model convergence speed and stability, d) LQO success
stems directly from their model’s architecture and how its embedding space
is structured, and finally e) the classic optimizer is still the go-to
solution to almost anything generalization-related.
EXAMINATION COMMITTEE:
Dr. Georgia Koutrika, Research Director, Information Management Systems
Institute, Athena Research Center
Prof. Nikos Mamoulis, Department of Computer Science and Engineering,
University of Ioannina
Assistant Prof. Vasilis Efthymiou, Department of Informatics and
Telematics, Harokopio University of Athens
24 October 2025
14:00 – 15:30 (GTB)
Join Microsoft Teams Meeting
https://teams.microsoft.com/l/meetup-join/19%3ameeting_OWI5NDQzODEtODNmYS00ZTkyLWI2NzktYjE0Y2U2NDRhNzI5%40thread.v2/0?context=%7b%22Tid%22%3a%226ae07702-c5f7-4f38-9b87-acad62a75d93%22%2c%22Oid%22%3a%22a532b5cb-e712-4935-a736-a15e0a5058ef%22%7d
Meeting ID: 314 577 906 602 1
Passcode: 3ae7HZ37
MSc Thesis presentation of Ms. Izabella Gogaeva, Thursday, October 9, 2025
On Thursday, October 9, 2025, at 14:00, Ms. Izabella Gogaeva of the postgraduate
program “Data Science and Information Technologies”, track on “Bioinformatics – Biomedical Data Science”, will present her MSc thesis titled:
Integrative Deep-Learning and Transcriptome-Resolved Framework for Discovery of Cryptic Splicing Variants in Breast Cancer
Abstract
Alternative splicing is a major source of transcriptomic diversity and is often disrupted in cancer. This work introduces an integrative framework that combines deep learning–based predictions from SpliceAI with isoform-level RNA-seq analysis to identify cryptic and dysregulated splicing events in breast cancer.
Using whole-genome and RNA-seq data from 89 TCGA-BRCA patients, candidate splice-altering variants were prioritized (Δ ≥ 0.2) and linked to changes in transcript structure and expression. Results showed that indels more frequently corresponded to differential isoform expression than SNVs, particularly in loss-type events associated with transcript downregulation.
This study highlights the potential and current limitations of integrating predictive and transcriptomic evidence to interpret noncoding variants in cancer.
EXAMINATION COMMITTEE:
Dr. Theodoros Dalamagas, Research Director, Information Management Systems Institute, Athena Research Center
Dr. George Georgakilas, Scientific Associate, ATHENA Research Center
Prof. Αrtemis G. Hatzigeorgiou, Professor of Bioinformatics, Department of Computer Science and Biomedical Informatics, University of Thessaly
9 October 2025
14:00 – 15:00 (GTB)
Join Zoom Meeting
https://us05web.zoom.us/j/82549680759?pwd=1aUUWbiN120Rbile77gEkIoyaVnraS.1
Meeting ID: 825 4968 0759
Passcode: 1i9wU1