Module 5 - Data Science & Machine Learning ll

In module five, you will learn several more methods used for machine learning in finance. Starting with unsupervised learning, deep learning and neural networks, we will move into natural language processing and reinforcement learning. You will study the theoretical framework, but more importantly, analyze practical case studies exploring how these techniques are used within finance.

Sections

Accordion Heading

Unsupervised Learning |

Accordion Content

  • K Means Clustering
  • Self Organizing Maps
  • Strengths and Weaknesses of HAC and SOM
  • Applications in Finance

Accordion Heading

Unsupervised Learning II

Accordion Content

  • The curse of dimensionality
  • t-distributed Stochastic Neighbor Embedding (t-SNE)
  • Uniform Manifold Approximation and Projection (UMAP)
  • Autoencoders
  • Applications in Finance

Accordion Heading

Deep Learning and Neural Networks

Accordion Content

  • What are Artificial Neural Networks and Deep Learning?
  • Perceptron Model, Backpropagation 
  • Neural Network Architectures: Feedforward, Recurrent, Long Short Term Memory, Convolutional, Generative adversarial
  • Applications in Finance

Accordion Heading

Natural Language Processing

Accordion Content

  • Pre Processing
  • Word vectorizations, Word2Vec
  • Deep Learning and NLP Tools
  • Application in Finance: sentiment change vs forward returns; S&P 500 trends in sentiment change; Earnings calls analysis.
  • Code examples

Accordion Heading

Reinforcement Learning I

Accordion Content

  • Recap of multi-armed bandit
  • The exploitation-exploration trade-off
  • Exploration strategies: softmax versus epsilon-greedy
  • Risk-sensitivity in Reinforcement-learning

Accordion Heading

Reinforcement Learning II

Accordion Content

  • Reinforcement Learning Case Study
  • Application of algo trading
  • Application in automated market making

Accordion Heading

AI Based Algo Trading Strategies

Accordion Content

  • Basic Financial Data Analysis with Python and Pandas
  • Creating Features and Label Data from Financial Time Series for Market Prediction
  • Application of Classification Algorithms from Machine Learning to Predict Market Movements
  • Vectorized Backtesting of Algorithmic Trading Strategies based on the Predictions
  • Risk Analysis for the Algorithmic Trading Strategies

Accordion Heading

Practical Machine Learning Case Studies for Finance

Accordion Content

  • Asset Price Behaviour and Volatility modeling
  • Empirical SDEs with estimated drift and diffusion functions
  • Generalized Stoch Vol models, learning dynamical models from data
  • Option pricing and hedging using Machine Learning
  • Model free pricing of exotic options
  • Robust Portfolio Optimization with Machine Learning
  • Denoising and Detoning covariance matrices
  • Nested Cluster Optimization

Accordion Heading

Quantum Computing in Finance

Accordion Content

  • Define quantum computing
  • Review the three key ingredients of quantum computing: qubits, quantum gates and quantum circuits
  • Enumerate some of the applications of quantum computing in various fields
  • Construct a simple quantum circuit online using the IBM Quantum Experience
  • Learn how to write your own quantum program using the Python module Qiskit
  • Review some financial applications of quantum computing, in particular European Call Options

Message Text

Lecture order and content may occasionally change due to circumstances beyond our control; however this will never affect the quality of the program.

Data Science & Machine Learning l
Fixed Income & Credit