Unit of competency Outline

Date retreived
22/07/2026 3:34 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.

Train and evaluate machine learning models

Train and evaluate machine learning models

Unit of competency
National Code
ICTAII502
State Code
ODT13
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 train and evaluate the operations of machine learning (ML) models when processing previously unseen data.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. Evaluate data requirements
  • 1.1 Confirm work brief and tasks according to organisational policies and procedures
  • 1.2 Analyse ML requirements according to cross-industry standard process for data mining (CRISP-DM) methodology, where required
  • 1.3 Confirm input machine training data source according to work brief
  • 1.4 Confirm that data attribute names contain target according to work brief
  • 1.5 Review data transformation instructions according to work brief
  • 1.6 Confirm that default and non-default training parameters control required learning algorithm according to work brief
2. Arrange machine training datasets
  • 2.1 Set machine training data parameters according to work brief
  • 2.2 Select model size according to work brief
  • 2.3 Use selected parameter and feature engineering on required training data
  • 2.4 Finalise machine training data procedures according to work brief
3. Arrange validation datasets
  • 3.1 Set validation data parameters according to work brief
  • 3.2 Select model size according to work brief
  • 3.3 Use selected parameter and feature engineering on required validation data
  • 3.4 Identify any functionality issues of parameters
  • 3.5 Refine ML parameters according to work brief
4. Arrange test datasets
  • 4.1 Set test data parameters according to work brief
  • 4.2 Select model size according to work brief
  • 4.3 Use selected parameter and feature engineering on required test data
  • 4.4 Identify and rectify any functionality issues in test dataset
  • 4.5 Finalise test data procedures according to work brief
5. Finalise ML evaluations
  • 5.1 Review target data outputs according to work brief
  • 5.2 Adjust model based on any discrepancies of outputs, where required
  • 5.3 Record predictive accuracy of ML model according to work brief
  • 5.4 Run variables through ML model and record outputs
  • 5.5 Compare outputs returned by ML model against target data outputs
  • 5.6 Document metrics and accuracy of ML data predictions according to organisational policies and procedures
No information
No information
No information