cart Cart
Your cart
Your cart is empty

Browse courses to find something that interests you.

Register search

Advanced Data Science for Innovation (online)

Learn how to design and implement innovative solutions to challenging, real-world business problems using advanced machine learning concepts and techniques, with one of the industry’s leading data science experts.

About this course

Take the next step in learning how to design and implement innovative solutions to complex problems using state-of-the-art machine learning algorithms and data science approaches.

Co-designed by renowned academics and industry partners from the UTS Master of Data Science and Innovation program and delivered one of the industry's leading experts, Anthony So, this interactive course will allow you to leverage the latest data science approaches and best practices to transform your approach to developing data-driven insights and solutions within any organisation.

In this course, you will learn advanced machine learning concepts and techniques in depth, such as machine learning pipeline, versioning, gradient boosting and neural networks. You will also gain skills that help you better manage production-ready end-to-end solutions.

Featuring a uniquely transdisciplinary approach to learning, this course will give you advanced skills in tackling complex problems, providing transferrable skills across a broad range of industries, sectors and organisations.

This dynamic, innovative approach, combined with hands-on learning and practice will help you become well versed in implementing, optimising and maintaining advanced machine learning solutions that can disrupt industries or change people’s lives for the better.

Course outline

The course will cover the following content:

Improving machine learning results

  • Imbalanced dataset
  • Multiple data sources
  • Interactive data visualisation
  • Automatic feature engineering.

Advanced machine learning algorithms

  • Polynomial linear regression
  • Support vector machine
  • Hierarchical clustering
  • Xgboost
  • Principal component analysis
  • Neural networks.

Optimising machine learning models

  • Regularisation
  • Cross-validation
  • Model interpretation
  • Automatic hyperparameter tuning.

Deploying machine learning solutions

  • Experiment tracking
  • Machine learning pipelines
  • Machine learning versioning.

Course learning objectives

By the end of the course you will be able to:

  • Manage a machine learning project end-to-end
  • Define relevant approaches for complex situation
  • Design and run experiments for machine learning
  • Train advanced machine learning models such as Xgboost or Neural Networks
  • Optimise a machine learning model
  • Build and automate machine learning pipeline
  • Manage machine learning model lifecycle.

Key benefits of this microcredential

This microcredential aligns with the 4-credit point subject, Advanced Data Science for Innovation (36114) in the Master of Data Science and Innovation (C04372). This microcredential may qualify for recognition of prior learning at this and other institutions.

Who is this course for?

This course is suitable for anyone interested in learning more about machine learning, such as:

  • Business analysts
  • Data analysts
  • Developers
  • Entrepreneurs
  • Project managers
  • Product owners.

Course information

Teaching and learning strategies

This course is offered in a series of six weekly, three hour interactive online sessions facilitated by a leading industry expert. Each session consists of a mix of course presentations and hands-on experience. Participants will be able to learn the theory behind machine learning algorithms and data mining techniques followed by practical workshops where they will apply their learnings on real-world business use cases.

In between sessions, participants will engage in individual and collaborative online activities designed to support the understanding of the machine learning algorithms and their application.

Assessment criteria

Assessment task: Machine Learning Project

  • Type: Project
  • Groupwork: Group and individually assessed
  • Weight: 50%.

Assessment task: Kaggle Competition

  • Type: Report
  • Groupwork: Individual
  • Weight: 50%.

Minimum requirements

  • Participants must achieve at least 50% of the course’s total marks and complete all assessments.
  • Before enrolling, participants with more limited experience might like to consider completing the microcredential, Applied Data Science for Innovation, but completion of that course is not a mandatory prerequisite for enrolling in this course.

Please contact us at if you have any questions about this course or requirements.

Mandatory requirement

  • This course is designed for participants with some knowledge of programming, data analysis or statistics.


A discount of 10% is available to UTS alumni or UTS staff enrolling in this microcredential. If you’re eligible for this discount, please ensure you have provided your UTS Student or Staff ID number in your UTS Open Profile (under 'A bit about you').

When signing up for the session, use the relevant voucher code to apply the discount to your cart:

  • UTS Student / Alumni: TDIalumni  (If you have forgotten your student ID number, please contact us at
  • UTS Staff: TDIstaff

Please note that discounts cannot be combined and only one discount can be applied per person per course session.

Register Your Interest

We use cookies

We use cookies to help personalise content, tailor and measure ads, plus provide a safer experience. By navigating the site, you agree to the use of cookies to collect information. Read our Cookie Policy to learn more.