Ponedeljkov seminar računalništva in informatike - Arhiv

ponedeljek, 8. junij 2026 Vedenje velikih jezikovnih modelov v napovednih trgih z različnimi udeleženci & A High-Rate Data Acquisition Protocol with Relative Topology Reconstruction & Machine learning models for predicting personal loan acquisition

V ponedeljek, 8. junija 2026, bodo ob 16:00 uri izvedena tri 
predavanja v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE
Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

ČAS/PROSTOR: 8. junij 2026 ob 16.00 prek Zoom-a.

1. predavanje:
============

-------------------------------------------
PREDAVATELJ: Marjan MEGLEN
-------------------------------------------

Marjan Meglen je magistrski študent Računalništva in informatike na UP FAMNIT.

-----------------------------------------------------------------------------------------------------------------------
NASLOV: Vedenje velikih jezikovnih modelov v napovednih trgih z različnimi udeleženci
-----------------------------------------------------------------------------------------------------------------------

POVZETEK:

V seminarju bo predstavljena analiza vedenja velikega jezikovnega modela pri napovedovanju izidov na napovednih trgih. Osrednje vprašanje seminarja je, ali se napovedi modela spreminjajo glede na informacije, ki jih model prejme v pozivu. Eksperiment vključuje tri neodvisne spremenljivke: vrsto drugih udeležencev trga, prikaz trenutnih tržnih verjetnosti in prikaz relevantnih novic. Model je za posamezen trg in datum podal napovedano verjetnost, da se bo trg razrešil v izid YES. Rezultati kažejo, da ima prikaz tržnih verjetnosti najmočnejši in najbolj konsistenten vpliv na napovedi modela, novice imajo prav tako izrazit, vendar tržno specifičen učinek, medtem ko je vpliv vrste drugih udeležencev šibkejši in manj konsistenten. S tem seminar pokaže, da so napovedi velikih jezikovnih modelov v napovednih trgih najbolj občutljive na neposredne informacije o trgu in dogodku.

Seminar bo potekal v slovenskem jeziku.

=============================================================================================================

2. predavanje:
============

--------------------------------------
PREDAVATELJ: Blaž JERMAN
--------------------------------------

Blaž Jerman is a student of the master's program Computer Science at UP FAMNIT.

----------------------------------------------------------------------------------------------------------------------
NASLOV: A High-Rate Data Acquisition Protocol with Relative Topology Reconstruction
----------------------------------------------------------------------------------------------------------------------

POVZETEK:

In this seminar, a protocol for rapid data collection in wired sensor networks will be presented. The focus will be on the use of simple UART communication and on the way sensor nodes collect and forward data toward a central node. The seminar will also introduce an automatic reconstruction of the network’s relative topology, which reduces the need for manually defining connections between sensors. Finally, measurement results obtained using linear and tree-based network structures will be presented as case studies for evaluating the protocol’s performance.

Seminar bo potekal v angleškem jeziku.

=============================================================================================================

3. predavanje:
============

---------------------------------------------------
PREDAVATELJICA: Pika POVH MAVRIČ
---------------------------------------------------

Pika Povh Mavrič is currently completing her master’s studies in Computer Science at UP FAMNIT. She works as a data analyst in the Customer Relationship Management department at a bank, where she applies and deepens her expertise in data analytics. Her work involves automating processes, improving data quality, creating various reports and analyses, and applying data-driven decision-making to everyday processes within the department. The topic of her paper aligns well with her work in the banking sector.

------------------------------------------------------------------------------------------------------
NASLOV: Machine learning models for predicting personal loan acquisition
------------------------------------------------------------------------------------------------------

POVZETEK:

In modern retail banking, the traditional approach of mass marketing consumer loans is becoming highly inefficient and often leads to customer fatigue. To address this issue, this research project focuses on developing a machine learning model designed to accurately predict a customer's intent to acquire a personal loan. By analyzing historical data, including demographics, product ownership, and past marketing engagement, the project uncovers hidden behavioral patterns. This predictive approach allows financial institutions to shift towards a more customer-centric strategy, optimizing marketing resources and offering loans only to those who truly need them.

Seminar bo potekal v angleškem jeziku.

=============================================================================================================

Seminarji bodo potekali online prek aplikacije Zoom s pričetkom ob 16:00 uri na sledeči povezavi:

https://upr-si.zoom.us/j/297328207?pwd=S3Zpdk1VR3pjckNtWkQwKzlvcDR5UT09

Meeting ID: 297 328 207
Passcode: 123456789

Vabljeni!

---

ponedeljek, 1. junij 2026 Kosar SEYYEDHOSSEINZADEH in Asmir KADUŠIĆ

---