Program Overview

Unit Overview

The unit DTSC630 - Predictive Analytics is designed to equip students with the knowledge and practical skills to design, implement, and communicate predictive models that support informed decision-making and innovation across a range of domains.

Unit Rationale, Description, and Aim

The ability to anticipate outcomes and make data-driven decisions is fundamental to success across industries. Predictive modelling and analytics leverage historical and current data through statistical, machine learning, and deep learning techniques to estimate future behaviour, identify patterns, and inform strategic decisions.

Learning Outcomes

To successfully complete this unit, students will be able to:

• Critically evaluate the use of predictive analytic approaches in decision making.
• Design reproducible predictive analytic solutions to real-world problems using appropriate techniques.
• Evaluate the selection, implementation, and use of predictive analytics solutions.
• Communicate predictive analytics solutions to stakeholders and interpret outcomes to inter-disciplinary audiences.

Unit Content

Topics will include:

• Introduction to Predictive Analytics and Data Types
• Data Fundamentals and Exploratory Analysis
• Data Preparation and Pre-processing for Predictive Modelling
• Feature Engineering and Predictive Models
• Machine Learning and Forecasting Techniques
• Deep Learning for Predictive Analytics
• Model Evaluation and Selection
• Deployment and Communication of Predictive Models
• Future Trends and Industry Applications

Assessment Strategy and Rationale

Assessments in this unit are designed to develop both conceptual understanding and practical skills in predictive analytics. The sequence scaffolds learning by moving from individual critical analysis to collaborative application using real-world data.

Assessment Task 1: Written Report and Computer Program

Students will critically evaluate and compare predictive-analytics techniques, discussing their benefits and limitations in supporting data-driven decision making.

• Weighting: 40%
• Learning Outcomes: LO1, LO2, LO3, LO4
• Graduate Capabilities: GC1, GC7, GC10, GC11

Assessment Task 2: Written Report, Presentation, and Q&A

Students will work collaboratively on a predictive-analytics project to design, implement, and evaluate a Python-based model addressing a business or industry problem.

• Weighting: 60%
• Learning Outcomes: LO1, LO2, LO3, LO4
• Graduate Capabilities: GC1, GC2, GC4, GC6, GC7, GC8, GC10, GC11

Learning and Teaching Strategy and Rationale

To develop the technical expertise and professional competencies required for vocational outcomes, students will engage in hands-on problem-solving activities that promote active learning, critical thinking, and collaborative engagement.

Representative Texts and References

• Ali, N.A. (2024). Predictive Analytics for the Modern Enterprise: a practitioner's guide to designing and implementing solutions. O'Reilly Media.
• Auffarth, B (2021). Machine Learning for Time-Series with Python. Packt Publishing
• Delen, D. (2021). Predictive Analytics: data mining, machine learning and data science for practitioners (2nd ed.). Person FT Press PTG.
• Géron, A. (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O'Reilly Media.
• Guido, S (2016). Introduction to Machine Learning with Python: A guide for data scientists. O'Reilly Media Inc.
• Joseph. M. & Tackes. J. (2024). Modern Time Series Forecasting with Python: Explore industry-ready time series forecasting using modern machine learning and deep learning (2nd ed.). Packt Publishing.
• Lasseri, F. (2021). Machine Learning for Time Series Forecasting with Python. Wiley
• Nielsen. A. (2019). Practical Time Series Analysis: Prediction with Statistics and Machine Learning. O'Reilly Media.
• Singh, H., Birla, S., Ansari, M.D. & Shukla, N.K. (2024). Intelligent Techniques for Predictive Data Analytics. IEEE.
• VanderPlas, J. (2026). Python Data Science Handbook: Essential tools for working with data. O'Reilly Media.
• Yu, B. & Barter, R.L. (2024). Veridical Data Science: The practice of responsible data analysis and decision making. MIT Press.

Credit Points and Year

• Credit points: 10
• Year: 2026