Key Takeaways
Upon completion of this 4-day Advanced Machine Learning for Financial Services Python-based course, attendees will learn how to (in the context of finance sector):
- Analyse and select the type of algorithm suited for their data science problem
- Implement and evaluate bagging, boosting, and ensemble methods
- Evaluate the architectural considerations for different use-cases and 1-2 implication examples for deployment and monitoring
- Create PyTorch environment for practical usage based on understanding of the advancements in deep learning for financial domain
- Implement and evaluate autoencoders in PyTorch based on understanding of autoencoders at a conceptual level
- Evaluate considerations when using RNN for a real world financial application based on understanding of the RNN architecture
- Implement and evaluate some of the deep learning techniques on a relevant case-study given as a class exercise
- Evaluate the suitability of various ML/AI algorithm usage in Finance
- Analyse the role of MLOps and the role of responsible & explainable AI in financial services along with some practical examples
Who Should Attend
This course has been currently designed to be suitable for participants working in banking/finance, regulatory sector and performing following roles:
- Data Analyst
- Financial analysts
- Data Scientist
- AI Expert
- Regulators
- Data engineers
- AI product managers
- Data science project managers
- Underwriters
- Pricing Actuaries
- Head of claims
- Business intelligence analysts
Pre-requisites:
- Working knowledge in the finance sector
- Good understanding of AI/ML
- Experience and involved in AI/ML projects in the finance sector
- Comfortable with programming in Python and PyTorch
- Comfortable with using Google Colab notebooks
What to Bring
No printed copies of course materials are issued.
Participants must bring their internet-enabled computing device (laptops, tablet etc) with power charger to access and download course materials.
If you are bringing a laptop, please see below for the tech specs:
|
|
Minimum
|
Recommended
|
|
Operating Systems
|
• Windows 7, 8, 10 or
• Mac OS
|
Laptop running the latest
version of either Windows or
Mac OS
|
|
System Type
|
32-bit
|
64-bit
|
|
Memory
|
8 GB RAM
|
16+ GB RAM
|
|
Hard Drive
|
256 GB disk size
|
|
|
Others
|
• An internet connection – broadband wired or wireless
• Installation permissions (non-company laptops)
• Keyboard
• Mouse/Trackpad
• Display
• Power adapter (laptop battery might run out) |
DirectX 10 graphics card for graphics hardware acceleration
|
Additional Software Requirements:
• Python (Anaconda)
• Google Colab
What Will Be Covered
This course will cover:
- Introduction to Tree-Based methods, bagging and boosting algorithms
- Application of boosting and ensemble methods in finance
- Different architectures of Neural Networks and advancement over time
- Introduction to Deep Learning and PyTorch framework for modelling in general
- Introduction to Auto-Encoders and application into Financial modelling
- Introduction to Recurrent Neural Network and application into financial modelling
- Mini-project
- Use case and evaluation of ML/AI applications in finance
- High-level introduction to MLOps and Responsible AI
Fees & Subsidies
Fees for 2024
| |
Full Fee |
Singaporeans & PRs
(self-sponsored) |
| Full course fee |
S$3600 |
S$3600 |
| ISS Subsidy |
- |
(S$360) |
| Nett course fee |
S$3600 |
S$3240 |
| 9% GST on nett course fee |
S$324 |
S$291.60 |
| Total nett course fee payable, including GST |
S$3924 |
S$3531.60 |
Note:
- All fees and subsidies are valid from January 2024, unless otherwise advised.
- All self-sponsored Singaporeans aged 25 and above can use their SkillsFuture Credit to pay for course fees. For more information about SkillsFuture Credit, click here.
- From 1st January 2024, the GST will be increased to 9%.
Certificate
Certificate of Completion
The ISS Certificate of Completion will be issued to participants who have attended at least 75% of the course.
Assessment Plan
This course aims to assess the participants’ technical Skills & competencies through the following means.
|
Type of assessments activity
|
Supporting materials
|
Assessed output
|
Assessment method (Individual)
|
|
Individual workshop
The course participants will carry out technical workshop with a given dataset/business case.
|
Workshop Handouts
|
Completed workshop outputs as an Individual
|
Workshop output graded on a “Pass / Fail” basis by ISS assessor
|
|
Individualwritten assessment
An individual written assessment that will test the understanding of key concepts/ skills / technical competencies
|
Assessment Paper/ online quiz
|
Completed answer book/ online quiz
|
Answer book / online quiz graded on a “Pass / Fail” basis by ISS assessor
|
Assessors will be domain experts from the ISS Teaching Staff (Instructor for this course).
To be deemed ‘Competent’ for each learning objective (skills & knowledge), participants must have achieved a mark of ‘Competent’ in all of the corresponding assessed activities.
TSC Description: Develop, select and apply algorithms and advanced computational methods to enable systems or software agents to learn, improve, adapt and produce desired outcomes or tasks. This also involves the interpretation of data, including the application of data modelling techniques to explore and address a specific issues or requirements.
TSC Proficiency Description: Level 5
- Develop and utilise new algorithms and advanced statistical models to enable production of desired outcomes
- Knowledge
- Industry developments and trends in analytics, algorithms and statistical modelling
- New and emerging data analytics and modelling tools and methodologies
- Broad range of algorithms and advanced programming techniques
- Elements of complex or advanced algorithms and computational models
- Applicability of various data analytics methodologies and techniques to address different business issues
- Abilities
- Direct data analytics and statistical modeling efforts across the organisation
- Make decisions on appropriate data analytics and computational methodologies to the problem
- Design complex or advanced statistical and computational methods
- Evaluate a brad range of algorithms and advanced computational methods to determine suitability for business context
- Spearhead the application of algorithms, models and computational techniques to new domains
- Establish guidelines for the creation and selection of effective algorithms and statistical models
- Synthesis critical findings and insights to address a significant business need or problem
Preparing for Your Course
NUS-ISS Course Registration Terms and Conditions
Find out more.
NUS-ISS and Learner’s Commitment and Responsibilities
Find out more.
WIFI Access
WIFI access will be made available to participants.
Venue
NUS-ISS
25 Heng Mui Keng Terrace
Singapore 119615
Click HERE for directions to NUS-ISS
In the event of a change of venue, participants are advised to refer to the acceptance email sent one week prior to the commencement date.
Course Confirmation
All classes are subject to confirmation and NUS-ISS will send an acceptance email to participants one week prior to the commencement date. Confirmed registrants are to attend and complete all lectures, class exercises, workshops and assessments (where applicable). Additionally, all responses to feedbacks and surveys conducted by NUS-ISS and its partners must be submitted. All training and assessments will be delivered as described in the course webpage.
General Enquiry
Please feel free to write to ask-iss@nus.edu.sg if you have any enquiry or feedback.