- Generative AI in the Banking industryTower Hall Unicredit Spazio Eventi, Milano, MI
Link to Youtube streaming:
https://www.youtube.com/@DataScienceMilanDon't forget to get your ticket on Eventbrite to register to the event:
https://www.eventbrite.it/e/biglietti-generative-ai-in-the-banking-industry-897320137687?aff=oddtdtcreatorEvent Agenda:
AI-powered search in banking knowledge bases - Andrea Galliani, Lorenzo Severini
Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to augment Large Language Models (LLMs) with external knowledge, including internal and private documents. In this context, we introduce UniMate, an internal search engine to empower bank employees, based on RAG architecture. UniMate enables efficient and smart retrieval of information related to products, processes, and internal procedures. During our discussion, we will delve into both engineering and data science aspects, providing an overview of the principal architectural and model choices. Additionally, we’ll address the main challenges associated with developing UniMate in a real-world banking context.Can LLM help create simulators for reinforcement learning? - Davide Villaboni
The application of reinforcement learning in the banking sector presents numerous challenges, with the primary obstacle being the lack of a secure environment suitable for simulating and effectively testing policies. To tackle this issue, we took a different approach by reframing the problem as a forecasting challenge. Our chosen model architecture incorporates a Large Language Model, and initial results suggest that this approach can effectively address our problem.Speaker bios:
Andrea Galliani is a ML Engineer and former Data Scientist at UniCredit. He received his PhD in Theoretical Physics in 2018 after completing a doctoral program between University of Padua, and University of Chicago. Prior to joining UniCredit, he spent two years as a post-doctoral researcher in Paris-Saclay University, working on high-energy physics and complex systems. After his post-doc, he joined a start-up as a Data Scientist, working on time series for complex systems. He finally joined UniCredit in 2022 where he’s currently working in the AI & DS team.
Lorenzo Severini is a researcher and data scientist at UniCredit. He received his PhD in Computer Science in 2017 after completing a joint doctoral program between Gran Sasso Science Institute and IMT Lucca. Prior to joining UniCredit, he spent three years at ISI Foundation in Turin. Lorenzo actively serves the scientific community by participating in various organizational and program committees and has published his works at premier AI, data mining and algorithms conferences.
Davide Villaboni is a Data Scientist with a strong technical foundation rooted in his M.Sc. in computer engineering. He began his journey with UniCredit in 2016, starting as a software engineer. before moving to the Data Science team, in 2020. Motivated by his passion for continual growth and innovation, Davide decided to expand his expertise in 2023 by pursuing a PhD at the University of Verona, focusing specifically on reinforcement learning for banking.---
Event details
This event is hosted by UniCredit at the Tower Hall, "via Fratelli Castiglioni 12", located in Piazza Gae Aulenti, Milan. The event will be held in English. At the end of the talks will follow a networking aperitif with food and drinks.Attending in presence:
This event is hosted by UniCredit. There will be 100 seats reserved to the community. If the tickets are sold out you can register on the waitlist, we will apply a first-in first-out policy to assign seats in case of cancellations.Attending remotely:
The event will be streamed live on our Youtube channel (https://www.youtube.com/c/DataScienceMilan).Event timeline:
- 18:45 – Open for external audience
- 19:00 – Event starts
- 19:00-19:10 – Opening from UniCredit, meetup short presentation
- 19:10-19:40 – First speech: AI-powered search in banking knowledge bases (Andrea Galliani, Lorenzo Severini)
- 19:40–20.00 Second Speech: Can LLM help creating simulators for reinforcement learning? (Davide Villaboni)
- 20.00 – 20.15 – Q&A & closing remarks
- 19:45–21:00 – Networking event
---
Would you be happy to host one of our events? Increase your popularity and be known by our community by hosting one of our interesting events. Contact us at datasciencemilan@gmail.com.If you are interested in doing a lightning talk or want to propose an event, hackathon, panel discussion, roundtable, or any sort of initiative please submit your proposal by getting in touch with a member of the staff. More info at https://www.linkedin.com/company/data-science-milan/
---
This event is supported by IAML (Italian Association of Machine Learning).