Assessor Resource

ICTDAT503
Use unsupervised learning for clustering

Assessment tool

Version 1.0
Issue Date: May 2024


This unit describes the skills and knowledge required to cluster data extracts from big data following unsupervised machine learning methodologies and report on the findings.

It applies to individuals who work in roles including, data analysts, data scientists, machine learning engineers, developers and programmers, and are responsible for data mining and machine learning activities with big data within medium to large organisations.

No licensing, legislative or certification requirements apply to this unit at the time of publication.

You may want to include more information here about the target group and the purpose of the assessments (eg formative, summative, recognition)


Evidence Required

List the assessment methods to be used and the context and resources required for assessment. Copy and paste the relevant sections from the evidence guide below and then re-write these in plain English.

The candidate must demonstrate the ability to complete the tasks outlined in the elements, performance criteria and foundation skills of this unit, including evidence of the ability to:

collect, prepare and cluster data using unsupervised machine learning methodologies and report on the findings on at least two occasions.

In the course of the above, the candidate must:

research industry standard approaches and methodologies for machine learning

evaluate and prepare data.

The candidate must be able to demonstrate knowledge to complete the tasks outlined in the elements, performance criteria and foundation skills of this unit, including knowledge of:

methodologies for data clustering unlabelled data including intra-cluster cohesion and intra-cluster separation

industry standard data clustering methodologies including benchmark modelling techniques for data clustering

report writing methodologies relevant to reporting findings of data clustering activities

industry standard machine learning methodologies relevant to unsupervised learning

methodologies for modelling data relevant to unsupervised learning.

Assessment must be conducted in a safe environment where evidence gathered demonstrates consistent performance of typical activities experienced in the customer service field of work and include access to:

hardware and software and components required for using unsupervised learning for clustering

organisational data reporting style guide and reporting processes required for unsupervised learning and machine learning

a site where activities can be carried out.

data required for clustering.

Assessors of this unit must satisfy the requirements for assessors in applicable vocational education and training legislation, frameworks and/or standards.

Submission Requirements

List each assessment task's title, type (eg project, observation/demonstration, essay, assingnment, checklist) and due date here

Assessment task 1: [title]      Due date:

(add new lines for each of the assessment tasks)

Assessment Tasks

Copy and paste from the following data to produce each assessment task. Write these in plain English and spell out how, when and where the task is to be carried out, under what conditions, and what resources are needed. Include guidelines about how well the candidate has to perform a task for it to be judged satisfactory.

The candidate must demonstrate the ability to complete the tasks outlined in the elements, performance criteria and foundation skills of this unit, including evidence of the ability to:

collect, prepare and cluster data using unsupervised machine learning methodologies and report on the findings on at least two occasions.

In the course of the above, the candidate must:

research industry standard approaches and methodologies for machine learning

evaluate and prepare data.

The candidate must be able to demonstrate knowledge to complete the tasks outlined in the elements, performance criteria and foundation skills of this unit, including knowledge of:

methodologies for data clustering unlabelled data including intra-cluster cohesion and intra-cluster separation

industry standard data clustering methodologies including benchmark modelling techniques for data clustering

report writing methodologies relevant to reporting findings of data clustering activities

industry standard machine learning methodologies relevant to unsupervised learning

methodologies for modelling data relevant to unsupervised learning.

Assessment must be conducted in a safe environment where evidence gathered demonstrates consistent performance of typical activities experienced in the customer service field of work and include access to:

hardware and software and components required for using unsupervised learning for clustering

organisational data reporting style guide and reporting processes required for unsupervised learning and machine learning

a site where activities can be carried out.

data required for clustering.

Assessors of this unit must satisfy the requirements for assessors in applicable vocational education and training legislation, frameworks and/or standards.
Copy and paste from the following performance criteria to create an observation checklist for each task. When you have finished writing your assessment tool every one of these must have been addressed, preferably several times in a variety of contexts. To ensure this occurs download the assessment matrix for the unit; enter each assessment task as a column header and place check marks against each performance criteria that task addresses.

Observation Checklist

Tasks to be observed according to workplace/college/TAFE policy and procedures, relevant legislation and Codes of Practice Yes No Comments/feedback
Research organisation’s need for data clustering and define problem, objective and outputs 
Determine required machine and input data set according to task requirements 
Define evaluation protocol and accepted measure of success 
Develop and document required benchmark model 
Collect data according to task requirements 
Evaluate data quantity, completeness and alignment according to task requirements 
Transform and format data according to specifications 
Finalise data preparation according to task requirements 
Input raw data according to task requirements 
Run required algorithm and adhere to required processing time frame 
Obtain output reports and determine completeness of task according requirements 
Analyse data report and determine clustering tasks have been completed according to task requirements 
Interpret, summarise and document findings 
Communicate findings to required personnel and seek and respond to feedback 
Lodge documentation according to task requirements and finalise task activities according to organisational requirements 

Forms

Assessment Cover Sheet

ICTDAT503 - Use unsupervised learning for clustering
Assessment task 1: [title]

Student name:

Student ID:

I declare that the assessment tasks submitted for this unit are my own work.

Student signature:

Result: Competent Not yet competent

Feedback to student

 

 

 

 

 

 

 

 

Assessor name:

Signature:

Date:

Assessment Record Sheet

ICTDAT503 - Use unsupervised learning for clustering

Student name:

Student ID:

Assessment task 1: [title] Result: Competent Not yet competent

(add lines for each task)

Feedback to student:

 

 

 

 

 

 

 

 

Overall assessment result: Competent Not yet competent

Assessor name:

Signature:

Date:

Student signature:

Date: