Singapore University of Social Sciences

Machine Learning, Deep Learning and Applications in Finance

Machine Learning, Deep Learning and Applications in Finance (FIN525)

Applications Open: 01 October 2022

Applications Close: 30 November 2022

Next Available Intake: January 2023

Course Types: Modular Graduate Course

Language: English

Duration: 6 months

Fees: $2200 View More Details on Fees

Area of Interest: Finance

Schemes: Alumni Continuing Education + (ACE+), Lifelong Learning Credit (L2C), Resilience

Funding: To be confirmed

School/Department: School of Business


Synopsis

FIN525 Machine Learning, Deep Learning and Applications in Finance aims to equip the students with model constructing and programming skills so that they can have a good understanding of the trending machine learning (ML) and deep learning (DL) techniques used in the financial industries. It introduces the concepts as well as fundamentals of classic algorithms and models in machine learning and deep learning. During the course, various financial data types and applications will be covered. It will help the students learn different machine learning and deep learning approaches in the financial context and gain experience applying the models to different financial data types and applications through multiple hands-on demonstrations and exercises using Python.

Level: 5
Credit Units: 5
Presentation Pattern: Every January

Topics

  • Understanding ML & DL
  • Fundamentals of classic ML models such as k-means, logistic regression, support vector machine (SVM)
  • Fundamentals of classic DL models such as Artificial Neural Network (ANN) and Convolutional Neural Network (CNN)
  • Introduction to different finance data types (e.g. time series data, cross-sectional data, and texts)
  • Framework of ML & DL Application in Finance
  • Risk analysis and forecasts using predictive modelling
  • Stock market prediction using multilayer neural network architecture
  • Textual analysis adopted in annual reports, media news and white papers
  • Sentiment analysis and topic modelling in Python
  • Portfolio analysis by machine learning
  • Python programming for machine learning
  • Python programming for deep learning

Learning Outcome

  • Assess various ML & DL models
  • Appraise the importance and application scenarios of ML and DL frameworks
  • Design ML and DL models to tackle financial issues and analyse model performance
  • Construct and implement deep learning and machine learning models in different financial practices
  • Compose sentiment analysis on textual data
  • Develop the programming skills used to model ML and DL applications in finance
Back to top
Back to top