Machine Learning for Finance
Introduction to key Machine Learning methods in finance
Scope of the Course
Get a grip on the disruptive forces that are enabling new, customer centric and lower-cost financial services.
Who is the intended audience for the course?
People in finance and allied industries who want to understand, implement or build new technology-driven financial services.
What is the need for this course, and why will participants benefit from it?
According to CapGemini, FinTech could add $512 billion to the global revenues of financial services firms by 2020.At the core of the FinTech revolution is Machine Learning - the ‘engine room’ of AI.
The aim of Machine Learning for Finance is to enable you to understand what kinds of Machine Learning algorithms can be applied to different kinds of practical financial scenarios.
The scenarios that we'll explore are:
- Insurance claims partitioning
- Customer segmentation
- Predicting interest rate rises
- Predicting interest rate values
- Predicting the value of stocks
- Portfolio development
- Finding market drivers
- Predicting market movements
The main Machine Learning methods that we'll use are:
- Random Forest Regression and ClassificationARIM
- LSTM Neural Network Regression
- K-means Clustering
- Principle Component Analysis
- Mean-Variance Portfolios
What are the learning outcomes?
At the end of this course, you will have acquired the following:
- Spot opportunities for AI and Machine Learning in your organisation
- Use key Machine Learning methods
- Apply Machine Learning to practical problems
- Understand the benefits and limitations of Machine Learning
- Key mathematical and coding concepts
- How Machine Learning works within a finance context
- Analyse and evaluate key Machine Learning capabilities
- Be able to frame Machine Learning opportunities
- Guide the development of a Machine Learning-based solution
- A development ‘sandbox' that you can use and customise after the course
- Starter code and data
- Data and model visualisation