AI for Finance

© Elephant Scale

September 2, 2022

Overview

  • AI is the new electricity. It will change the way we do everything. Financial institutions: banks, savings and loans, insurance, and mortgage companies, who are already well familiar from FinTech, are the first to derive benefit from AI. But every business can improve its money handling through AI. And the companies will soon discover that their use of AI is what allows it to bypass the competition and not be left behind.

  • The course is intended for financial specialists, FinTech users, software architects, and engineers. It gives the participants a practical level of experience, achieved through a combination of about 50% lecture, 50% demo work with student’s participation.

Benefits

  • After taking the course, participants will be able to

    • Find the low-hanging fruit for AI in Finance
    • Apply best practices for AI financial applications
    • Build fraud-resistant applications
    • Use text input for financial decisions

Duration

  • 3-4 days

Audience

  • Financial Professionals
  • FinTech Software Architects
  • Developers

Prerequisites

  • Interest in finance
  • Familiarity with a programming language

Lab environment

  • A working environment will be provided for students.

Course Outline

AI Overview

  • A brief history of AI
  • Types of AI systems
  • Training machine learning models
  • Applying models for prediction
  • Demos and Labs

AI for Structured Financial Data

  • Feature engineering
  • Data preparation
  • Standard machine learning
  • Advantages of deep learning with neural networks

Understanding Text

  • Simple methods: NLTK, TextBlos
  • TF-IDF
  • More text analysis with Spacy
  • Text analysis revolution of 2018

Fighting adversaries

  • GAN – Generative Adversaries Networks
  • Learning from mistakes – reinforcement learning
  • Learning to balance
  • Learning to trade

AI for Finance

  • Fairness (ch. Fighting bias)
  • Bias
  • Safety
  • Interpretability
  • Overcome regulatory hurdles

Fighting bias in financial decisions

  • Sources of unfairness in Machine Learning
  • Legal perspectives
  • Learning to be fair
  • Developing fair models

Real-world AI Implementations

    • Manage credit risk and reduce defaults
    • Use textual information to provide financial insights
    • Apply AI to personalized banking
    • Fraud prevention