Unit of competency Outline

Date retreived
22/07/2026 7:06 PM AWST

Whilst all efforts are made to provide accurate and timely information from the relevant source/documentation, please be aware that the information supplied may not be the most current version. The accuracy of the detail has not been confirmed by the Department and therefore should not be relied upon without first confirming the contents.

Automate work tasks using machine learning

Automate work tasks using machine learning

Unit of competency
National Code
ICTAII501
State Code
ODT22
TGA Status
Current
DTWD Status
Approved
Current Release Number
1.00
Current Release Date
03/02/2022
View on TGA
State Implementation and Classification
Approved Date
25/05/2022
Field of Education
020119 - Artificial Intelligence
Original Release Date
25/05/2022
Nominal Hours
55
Description
This unit describes the skills and knowledge required to use machine learning (ML) principles and techniques to support the automation of procedural tasks and improve organisational productivity.The unit applies to individuals who may work across a wide range of information and communications technology (ICT) roles, including support technicians, system administrators, programmers and cloud computing engineers.No licensing, legislative or certification requirements apply to this unit at the time of publication.
Notes
Elements and Performance Criteria
1. Organise required ML dataset
  • 1.1 Confirm ML work brief and tasks according to organisational policies and procedures
  • 1.2 Compare structured, unstructured, labelled and unlabelled machine training data according to work brief
  • 1.3 Randomise, deduplicate and check machine training data for imbalances and biases
  • 1.4 Analyse unbiased and biased dataset considerations according to work brief
  • 1.5 Divide data into training subset and evaluation subset according to work brief
2. Review data algorithms
  • 2.1 Confirm that data is correctly grouped as labelled or unlabelled
  • 2.2 Analyse regression algorithms, decision trees or neural net algorithms for labelled data, where required
  • 2.3 Analyse clustering, association, instance-based or neural network algorithms for unlabelled data, where required
  • 2.4 Document analysis findings according to organisational policies and procedures
  • 2.5 Select algorithm for dataset according to analysis findings
3. Create ML model
  • 3.1 Confirm expected ML outputs with required personnel
  • 3.2 Run variables through selected algorithm according to work brief
  • 3.3 Compare expected and actual ML outputs
  • 3.4 Adjust algorithm and re-run variables through selected algorithm according to work brief
  • 3.5 Confirm that new algorithm outputs yield accurate output results
  • 3.6 Compare expected and final outputs with required personnel
4. Use ML model for scoring
  • 4.1 Configure ML model into existing systems according to organisational policies and procedures
  • 4.2 Run organisational data through algorithm according to work brief
  • 4.3 Secure and save ML model according to organisational policies and procedures
No information
No information
No information