Ellipse-108.svg
Ellipse-110.svg
Group-17.svg
Group-17.svg
Group-17.svg

ICESCO Chair of Data Science and Analytics for Business esteblished at NUST SEECS, is organizing

A 03 Day Hands-on Workshop on

FinTech Frontier: Harnessing the Power of LLMs

Transformming Finance with Advanced Language Models

February 21-23, 2024Smart Classroom, NUST SEECS, Sector H-12, Islamabad

From 1400 – 1700 hrs

Participants have to bring their laptops

About The Workshop

The "FinTech Frontier: Harnessing the Power of LLMs" workshop, scheduled for February 21-23, 2024, is a comprehensive three-day, hands-on event designed to immerse participants in the world of Large Language Models (LLMs) within the finance sector. This innovative workshop aims to provide attendees with a solid foundation in understanding the fundamentals, applications, and integration of LLMs in financial systems. Covering a range of topics from algorithmic trading to fraud detection, and from ethical AI practices to regulatory compliance, participants will gain not only theoretical knowledge but also practical skills through case studies and hands-on sessions. With a focus on fine-tuning and customizing LLMs for specific financial applications, the workshop promises to equip attendees with the insights needed to leverage AI technology in transforming finance. Led by distinguished experts in the field, including Prof. Dr. Muhammad Moazam Fraz, Dr. Seemab Latif, Huma Ameer, and Sahar Arshad, this event is a must-attend for anyone keen on exploring the cutting-edge intersection of AI and finance. Participants are required to bring their laptops to fully engage in the interactive components of the workshop, ensuring a comprehensive learning experience that blends theory with practical application.

R.jpg

Workshop 2024

What you will Learn

1

Day 1: Introduction to Large Language Models and Basic Concepts

  1. Introduction to Large Language Models
    1. Overview of LLMs (GPT, BERT, etc.)
    2. Understanding the basics: Natural Language Processing (NLP) and Machine Learning (ML)
    3. Evolution and current state of LLMs
  1. LLMs in Finance: Opportunities and Challenges
    1. Application areas in finance (e.g., algorithmic trading, risk assessment, customer service)
    2. Benefits and limitations of using LLMs in finance.
    3. AI ethics and responsible AI in financial services
    4. Case studies of successful implementations
  1. Technical Overview
    1. Basics of how LLMs work (neural networks, training data, etc.)
    2. Understanding language processing and prediction models
    3. Data requirements and preparation for financial contexts
  1. Reading
2 & 3

Day 2 & 3: Advanced Applications and Integration

  1. Deep Dive into Financial Applications
    1. Advanced algorithms for trading and investment strategies
    2. Credit scoring and risk assessment.
    3. Fraud detection and anti-money laundering
  1. Integrating LLMs with Financial System
    1. Data integration and pipeline design
    2. Compliance and regulatory considerations
    3. Security and data privacy issues
  1. Customizing LLMs for Specific Finance Use Cases
    1. Fine-tuning and training models on finance-specific datasets
    2. Addressing biases and ensuring fairness in models
  1. Workshop
    1. Hands-on session to develop a simple finance related LLM application.
    2. Group activities and discussions.

Expected Outcomes

Comprehensive Knowledge of LLMs in Finance: Participants will leave with a deep understanding of LLMs, including their capabilities, limitations, and potential impact on various financial services.

Practical Skills and Insights: Through hands-on sessions and case studies, participants will gain practical experience in finetuning LLMs and insights into overcoming real-world challenges in integrating these models into financial systems.

Awareness of Ethical and Regulatory Considerations: Participants will learn about the importance of ethical AI practices, data privacy, and compliance with financial regulations when implementing LLMs in finance.

Case Studies From Finance Domain

1
  1. Advanced Algorithms for Trading and Investment Strategies
  • Algorithmic Trading: Using LLMs to analyse market sentiment from news articles, social media, and financial reports to make informed trading decisions.
  • Portfolio Management: Employing LLMs to optimize asset allocation, diversify investment portfolios, and assess market risks based on historical and current market data analysis.
  • Predictive Analytics: Leveraging LLMs to forecast market trends, stock prices, and economic indicators, helping traders and investors to anticipate market movements.
  • Event-Driven Strategies: Utilizing LLMs to identify and capitalize on market-moving events, such as mergers, acquisitions, or regulatory changes.
2

2. Credit Scoring and Risk Assessment

  • Credit Scoring Models: Implementing LLMs to analyse traditional and non-traditional data sources (e.g., social media, transaction history) for more accurate credit scoring, especially for individuals with limited credit history.
  • Risk Profiling: Using LLMs to assess borrower risk profiles more accurately by analysing a wide range of data points, including behavioural and transactional data.
  • Default Prediction: Employing LLMs to predict loan defaults more accurately by analysing patterns in historical data, economic indicators, and borrower behaviour.
  • Stress Testing: LLMs can be used to simulate various economic scenarios and assess the impact on credit portfolios, aiding in better risk management.
3

3. Fraud Detection and Anti-Money Laundering

  • Transaction Monitoring: Using LLMs to monitor and analyse transaction data in real-time to identify suspicious patterns indicative of fraud or money laundering.
  • Anomaly Detection: Implementing LLMs to detect unusual account behaviours that deviate from normal patterns, which could signify fraudulent activities.
  • KYC (Know Your Customer) Compliance: Leveraging LLMs to enhance the effectiveness of KYC processes by analysing and cross-referencing vast amounts of data for customer verification.
  • Network Analysis: Employing LLMs to analyse relationships and transactions between entities to uncover complex money laundering schemes.

Resource Persons

Picture16.jpg
Prof Dr. Muhammad Moazam Fraz

Director ICESCO Chair,
Professor and HoD ( AI & Data Science Department)
SEECS, NUST

seemab.png
Dr Seemab Latif

PhD (Artificial Intelligence), University of Manchester, UK

CEO and Founder Awaz AI

Associate Professor, AI & Data Science Dept,. SEECS NUST

huma-ameer.jpg
Huma Ameer

Data Analysis and Deep Learning

AI Team Lead, CPInS Lab, SEECS, NUST

sahar-arshad.jpg
Sahar Arshad

PhD Scholar, Natural Language Processing

NLP Team Lead, CPInS Lab, SEECS, NUST

Register for 3-Day Hands-on Workshop

Come join us on this exciting journey where theory meets practice, and data becomes a powerful tool for driving business success!

For details, please contact.

seemab.latif@seecs.edu.pk

Event Pictures

Event Pictures

Digital Presence and Online Visibility

1

Shared on NUST LinkedIn

Click Here
2

Shared on SEECS Event Page

Click Here

Digital Presence and Online Visibility

1

Shared on SEECS Events

Click Here

NUST: Facebook

SEECS: Facebook

MachVIS: Facebook

MachVIS: LinkedIn

ICESCO Chair: Twitter

ICESCO Chair: Facebook