AI @ AUEB Lecture Series
AI @ AUEB Lecture Series
On the occasion of a recent interdisciplinary article published in Nature (https://www.nature.com/articles/s41586-022-04448-z) and presented at AUEB (https://www.aueb.gr/el/content/ restoring-and-attributing-ancient-texts-using-deep-neural-networks-thea-sommerschield) but also the interested parties of AUEB’s academic and research community for issues related to Artificial Intelligence (AI) and sub-sectors (such as machine learning, natural language processing, computer vision), a series of lectures on these topics is planned.
The lectures will currently take place once a month, during which the projects produced by AUEB members of the academic and research community and/or guests, related to AI will be presented.
The aim of these lectures is to create collaborations, both between AUEB’s Departments and with external bodies and organizations, promoting the work of AUEB members, further strengthening existing collaborations, and possibly attracting additional resources.
The series of lectures is entitled AI @ AUEB and they will be presently broadcasted online via MS Teams.
Information about the first scheduled talk:
1st Lecture AI @ AUEB
Date / time: Tuesday 3 May 2022, 17: 15-18: 00
Title: "Machine learning in U.S. bank distressed delisting prediction: A text-based approach"
Speakers: N. Goumas, G. Leledakis, E. Pyrgiotakis, I. Androutsopoulos
MS Teams Link:
https://teams.microsoft.com/l/meetup-join/19%3aOiYUJgd5vTDTv9p0FnXvTdZ9TTZxIBRHwZzEpD02P-Y1%40thread.tacv2/1649780577695?context=%7b22a4a % 2c% 22Oid% 22% 3a% 225b49c8b5-6801-409c-a8f8-6e18215b3a08% 22% 7d
Amid advancements in technology, academics and practitioners are employing innovations in statistical methodology and incremental information sources to improve the economic health assessments of financial institutions. By employing textual analysis on U.S. Bank Holding Companies’ annual reports, having been filed over the period 1997-2018, we extract textual features based on bag of words (BOW) and embedding-based approaches. Then, we combine the extracted textual features with financial and market-driven variables as input to machine learning models to predict bank distressed delisting events. Our results suggest that for prediction horizons of one and two years of the filing date, the combination of these heterogeneous information sources serves incrementally accurate early warning signals in a distressed delisting prediction task. Therefore, our results contribute to micro prudential regulation by highlighting the importance of textual information in a bank distressed delisting prediction task.
The Organizing Committee of the AI @ AUEB lecture series:
Ion Androutsopoulos (Informatics)
Dimitris Karlis (Statistics)
Iordanis Koutsopoulos (Informatics)
Theodoros Lappas (M&C)
George Leledakis (Acc & Fin)
Panos Louridas (MS & T)
Giannis Ntzoufras (Statistics)
Stella Spilioti (B A)
Damianos Chatziantoniou (MS & T)
To receive updates on AI @ AUEB lecture series, you may send an e-mail to email@example.com, to subscribe to the email list of AI @ AUEB. To unsubscribe from the list, use firstname.lastname@example.org. Only lecture organizers can send messages to list members.
If you have an AUEB account and want to view all scheduled AI @ AUEB Lecture Series in your MS Teams calendar, subscribe to the "AI @ AUEB" group on MS Teams (code: r2dtl45). Team members can also send text messages (chat) to other team members.
To participate in the organization of lectures and speakers’ suggestions/selections, please, contact the organizing committee.