Advanced Data Science

Unit code:NIT3251Study level:Undergraduate

Credit points

12
(Generally, 1 credit = 10 hours of classes and independent study.)

Location

Footscray Park
VU Brisbane
VU Sydney

Prerequisites

NIT2002 - Data Science Methods and Applications; or
NIT2251 - Machine Learning and Data Mining
(Or equivalent to be determined by unit coordinator)
Co-requisites
(Corequisite units must be studied concurrently with this unit)

Overview

In this unit, you will develop a deep understanding of data exploration, visualisation, analysis, and advanced machine learning/deep learning techniques. You will gain hands-on experience with open-ended investigations of real-world practical dataset and novel data science problems. You will gain better understanding of the characteristics of different algorithms, tools, frameworks, and technologies. You will apply, evaluate, and develop advanced models such as CNN, LSTM, GNN, GAN, Transformer and LangChain. etc. By the end of the unit, you will be able to design data-driven solutions that support decision-making in roles such as AI development, research analytics, and applied machine learning.

Learning Outcomes

On successful completion of this unit, students will be able to:

Design advanced machine learning and deep learning applications to solve complex data science problems;
Evaluate diverse data science methodologies across various applications;
Design data-driven solutions with optimised performance and appropriate model interpretability individually and as part of a team;
Integrate ethical, legal, and social considerations into responsible data-driven decision-making;
Exhibit complex analytical insights effectively to diverse audiences, supporting business and research-driven applications.

Assessment

For Melbourne campuses

Assessment type: Test | Grade: 20%

Open test

Assessment type: Project | Grade: 40%

Applied problem solving - code, and report with demonstration and oral Q&A (Group)

Assessment type: Case Study | Grade: 40%

Case study and algorithm implementation - code, and report with Q&A verification

Test: Students complete an open test assessing their understanding of advanced machine learning and deep learning methodologies and their applications in data science problem-solving.

Project: Includes structured milestone reviews and in-class progress checks. Student's individual contributions are logged, validated, and justified through recorded peer review or demonstration to ensure authenticity.

Case Study: Students apply concepts to unpredictable data science scenarios. Responses are evaluated based on reasoning, method selection, and outcome justification, with an in-class component or oral Q&A verifying understanding.