Problem-Solving and Decision-Making (ICT5357) T1 Assignment Help

Assessment Brief: ICT5357 Problem-Solving and Decision-Making with Machine Learning Trimester 1, 2025

Assessment Overview

Assessment Task

Type

Weight

ing

Length

Due

ULOs

Asses

sed

Assessment 1: Supervised Machine  Learning Project

Implement a machine learning  model to perform a simple

classification or regression task.  Write a report outlining steps  taken.

Individual

20%

1000 (500

words for

report + 500  words for

model)

Week 4

ULO1

ULO2

ULO4

Assessment 2: Laboratory

Practicum

Regular invigilated practical tests,  implementing some machine  learning model or machine learning  analysis to solve a problem.

Individual

Invigilated

30%

2000 words  (1200

words for

report +

800 words

for model)

Weeks

6, 8

ULO1

ULO2

ULO3

ULO4

Assessment 3: Unsupervised  Machine Learning Project

Perform clustering and

dimensionality reduction on a  complex dataset and implement a  machine learning model to perform  a classification/regression task on  the reduced dataset. Write a report  outlining steps taken.

Group

25%

3000 words  (2000

words for

report +

1000 words  for model)

Week 7

ULO1

ULO3

ULO4

Assessment 4: Computer Vision  Case Study

Apply strategic problem-solving in a  domain involving visual data  analysis. Write a report outlining  steps taken.

Individual

25%

2500 words  (1500 words  for report +  1000 words  for model)

Week

12

ULO1

ULO2

ULO4

equiv. – equivalent word count based on the Assessment Load Equivalence Guide. It means this assessment is  equivalent to the normally expected time requirement for a written submission containing the specified  number of words.

Note for all assessments tasks:

● Students can generate/modify/create text generated by AI. They are then asked to  modify the text according to the brief of the assignment.

● During the preparation and writing of an assignment, students use AI tools, but may  not include any AI-generated material in their final report.

● AI tools are used by students in researching topics and preparing assignments, but  all AI-generated content

must be acknowledged in the final report as follows:

Format

I acknowledge the use of [insert the name of AI system and link] to [describe how it  was used]. The prompts used were entered on [enter the date in ddmmyyy:] [list the  prompts that were used]

Example

Tools

I acknowledge the use of ChatGPT to create content to plan  and brainstorm ideas for my assessment. The prompts used were entered on 18  March, 2023:

● What are some key challenges in running an online business?

Assessment 1: Supervised Machine Learning Project

Due date:

Week 4

Group/individual:

Individual

Word count/Time provided:

1000 (500 words for report + 500 words for model)

Weighting:

20%

Unit Learning Outcomes:

ULO-1, ULO-2, ULO-4

Assessment 1 Detail

You will be provided with a number of simple raw datasets that could be used for  classification or regression. You will choose one dataset and submit a report that outlines:

● A problem that could be addressed with the dataset

● A machine learning algorithm that could be used to train AI to answer this question

● Any preprocessing of data and other preparation that you would do for this training

You will also submit one or more models trained with the data. You are required to submit:

1. A document (1000 words) that includes:

○ What kind of problem could be solved and/or what kind of decisions could be  made, if an appropriate machine learning model were trained on this dataset ○ What such a model would do, either as a classification task or a regression  task

○ An explanation of how the dataset relates to the classification or regression  task

○ Any specific learning algorithms that might be particularly suitable or  unsuitable, given the dataset, and why

○ What preprocessing would you perform on the dataset, prior to machine  learning

○ An evaluation of the performance of the model

2. The project used to develop your model(s).

3. The deployed model(s)

Assessment 1 Marking Criteria and Rubric

The assessment will be marked out of 100 and will be weighted 20% of the total unit mark.

Marking

Criteria

Not satisfactory

(0-49%) of the criterion  mark

Satisfactory

(50-64%) of the

criterion mark

Good

(65-74%) of the  criterion mark

Very Good

(75-84%) of the

criterion mark

Excellent

(85-100%) of the

criterion mark

Problem

Solving

(20 marks)

Unable to identify and connect problems to  machine learning  models and training  data.

Able to identify and connect some

problems to

machine learning  models and training data.

Able to identify  and connect many  problems to

machine learning  models and

training data.

Able to identify and connect problems  to machine learning  models and training data.

Able to identify and  connect problems to  machine learning  models and training

data, and provide  clear explanations for these connections.

Data

(20 marks)

Explanation of the  dataset is missing or  contains significant  inaccuracies. No  modifications or pre processing are

performed, or

explanations are

unclear.

Dataset is

described with

basic details but  lacks clarity or

depth. Basic

modifications or  pre-processing  steps are

mentioned, but  their rationale is  unclear.

Explanation

provides a clear  overview of the  dataset, including  features, target  variable, and

relevance to the  task. Modifications or pre-processing  are adequately  explained and

justified.

Explanation is

thorough and

demonstrates a  strong grasp of  dataset

characteristics and  relevance.

Modifications or  pre-processing are  well-reasoned and  effectively

contribute to model development.

Explanation is

exceptional, offering  detailed insights into  features, target

variable, and

dataset’s role in the  task. Modifications or pre- processing are  exceptional, showing deep understanding  of their impact on the task.

Machine

Learning (20  marks)

Inappropriate

algorithms or

hyperparameters are  chosen, or

explanations are

missing.

Basic algorithms  are chosen, but  their suitability and  hyperparameters  are inadequately  explained.

Appropriate

algorithms are

selected,

relevance to the  task is justified  with reasonable  hyperparameters.

Algorithms are well suited to the task,  and

hyperparameters  are carefully tuned  with clear

reasoning.

Algorithm selection  and hyperparameter  tuning are

exceptional, showing deep understanding  of model choices.

Models (20

marks)

No model results  provided or results do not address the

problem.

Basic model results are mentioned but  lack context or

interpretation.

Provides some  meaningful

insights, and

results are

described clearly.

Model outcomes  are explained with  insight, their

implications are  well interpreted.

Model performance  is explained clearly,  interpretation shows  deep understanding.

Clarity and

Presentation (20 marks)

Answers are unclear,  disorganised, and  difficult to understand.

Answers are

somewhat clear,  but lack

organisation.

Answers are

mostly clear and  organised.

Answers are clear  and organised.

Answers are clear  and organised, easy  to understand, and  engaging or

insightful.

Assessment 2: Laboratory Practicum

Due date:

Weeks 6, 8

Group/individual:

Individual

Word count/Time provided:

2000 words (1200 words for report + 800 words for  model), 1000 words each

Weighting:

2x 15% = 30%

Unit Learning Outcomes:

ULO-1, ULO-2, ULO-3, ULO-4

Assessment 2 Detail

During one hour of the weekly seminar in Weeks 6 and 8, you will be provided with some  problem or decision that can be addressed with an appropriate machine learning approach.  You will be required to provide written answers, and in some weeks you will also be  required to provide one or more machine learning models to address the problem.

These assessments are held during two relevant weekly seminar and they are invigilated.

Assessment 2 Marking Criteria and Rubric

Each assessment will be marked out of 100 and will be weighted 15% of the total unit mark,  totalling a combined weight of 2 x 15% = 30%.

Marking

Criteria

Not satisfactory (0- 49%) of the criterion  mark

Satisfactory

(50-64%) of the  criterion mark

Good

(65-74%) of the  criterion mark

Very Good

(75-84%) of the

criterion mark

Excellent

(85-100%) of the

criterion mark

Problem

Solving (25  marks)

Unable to identify  and connect

problems to machine learning models and  training data.

Able to identify  and connect

some problems  to machine

learning models  and training

data.

Able to identify  and connect

many problems to machine learning  models and

training data.

Able to identify and connect problems  to machine

learning models  and training data.

Able to identify and  connect problems to  machine learning  models and training  data, and provide  clear explanations for these connections.

Data and

Machine

Learning (25  marks)

No relevant data  preprocessing, data  visualisations,

clustering,

dimensionality

reduction or time  series techniques  are used.

Some relevant  data

preprocessing,  data

visualisations,  clustering,

dimensionality  reduction or time  series

techniques, but  submission

contains errors

All/most relevant  data

preprocessing,  data

visualisations,  clustering,

dimensionality  reduction or time  series techniques  are used and

explained.

All relevant data  preprocessing,  data visualisations, clustering,

dimensionality

reduction or time  series techniques  are used and

explained well.

All relevant data

preprocessing, data  visualisations,

clustering,

dimensionality

reduction or time  series techniques are  used and explained  with excellent insight.

 

or omissions in  explanations.

Orange /

AutoML

techniques

(25 marks)

Machine learning  project is

disorganised and  difficult to follow.

Machine learning  project achieves  goals but with  little

organisation.

Machine learning  project is

somewhat

organised but  contains one or  more errors in the  workflow.

Machine learning  project is well

organised and

easy to follow.

Machine learning  project is

exceptionally

organised with a

logical workflow.

Clarity and  Presentation (25 marks)

Answers are

unclear,

disorganised, and  difficult to

understand.

Answers are

somewhat clear,  but lack

organisation.

Answers are

mostly clear and  organised.

Answers are clear  and organised.

Answers are clear  and organised, easy  to understand, and  engaging or insightful.

Assessment 3: Unsupervised Machine Learning Project

Due date:

Week 7

Group/individual:

Group

Word count/Time provided:

3000 words (2000 words for report + 1000 words for  model)

Weighting:

25%

Unit Learning Outcomes:

ULO1, ULO3, and ULO4

Assessment 3 Detail

You will be provided with a number of complex high-dimensional raw data sets. You will  choose one of these datasets and submit a report that outlines:

● A problem that could be addressed with the dataset

● How methods could be used to reduce the dimensionality of the dataset and uncover  structure in the dataset

● What kind of classification or regression could be performed with the data once the  complexity in the dataset has been reduced

You will also submit several models that have been trained with the data, including:

● A model trained on the raw dataset

● A model trained on the dataset after applying some dimensionality reduction  techniques

● A model trained on the dataset after manually choosing a selection of input features  in the training dataset

You are required to submit:

1. A document (3000 words) that includes:

○ What kind of problem could be solved and/or what kind of decisions could be made, if  an appropriate machine learning model were trained on this dataset

○ What such a model would do, either as a classification task or a regression task ○ An explanation of how the dataset relates to the classification or regression task ○ Insights gained from the raw data, including from visualisations of the data ○ An explanation of any dimensionality reduction techniques that could be used to  reduce the complexity of the raw data

○ Any specific learning algorithms that might be particularly suitable or unsuitable, given  the dataset, and why

○ What preprocessing would you perform on the dataset, prior to machine learning ○ An evaluation of the performance of the models

2. The project used to develop your models.

3. The deployed models.

Assessments 3 Marking Criteria and Rubric

The assessment will be marked out of 100 and will be weighted 25% of the total unit mark.

Marking

Criteria

Not satisfactory (0- 49%) of the criterion  mark

Satisfactory

(50-64%) of the  criterion mark

Good

(65-74%) of the  criterion mark

Very Good

(75-84%) of the  criterion mark

Excellent

(85-100%) of the  criterion mark

Problem

Solving (10

marks)

Unable to identify  and connect

problems to machine learning models and  training data.

Able to identify  and connect some problems to

machine learning  models and

training data.

Able to identify  and connect many  problems to

machine learning  models and

training data.

Able to identify  and connect

problems to

machine learning  models and

training data.

Able to identify  and connect

problems to

machine learning  models and

training data, and  provide clear

explanations for  these

connections.

Data (10

marks)

Explanation of the  dataset is missing or contains significant  inaccuracies. No  modifications or pre processing are

performed, or

explanations are  unclear.

Dataset is

described with  basic details but  lacks clarity or  depth. Basic

modifications or  pre-processing  steps are

mentioned, but  their rationale is  unclear.

Explanation

provides a clear  overview of the  dataset, including  features, target  variable, and

relevance to the  task. Modifications or pre-processing  are adequately  explained and

justified.

Explanation is

thorough and

demonstrates a  strong grasp of  dataset

characteristics  and relevance.  Modifications or  pre-processing  are well-reasoned  and effectively  contribute to

model

development.

Explanation is

exceptional,

offering detailed  insights into

features, target  variable, and

dataset’s role in  the task.

Modifications or  pre- processing  are exceptional,  showing deep

understanding of  their impact on the task.

Data

Visualisation  (15 marks)

Creates little or no  visualisations of  data, and/or offers  no explanation or  understanding of  their significance.

Creates

visualisations of  data, but offers on limited explanation of how these

visualisations

connect to insights into the problem.

Creates relevant  visualisations of  data. Presents  some insights

based on these  visualisations.

Creates relevant  and helpful

visualisations of  data. Presents  good insights

based on these  visualisations.

Clearly explains  how visualisations  of data connect to insights into the  problem space.

Dimensionality  Reduction (15  marks)

No dimensionality  reduction techniques are used and/or no  rationale given for  these.

Some

dimensionality  reduction

techniques are  used. Little

rationale given for these.

Explains some  dimensionality  reduction

techniques used  and offers some  rationale for these. Shows some

insight into

dimensionality  reduction.

Explains

dimensionality  reduction

techniques used  and the rationale  for these. Shows  good insight into

dimensionality  reduction.

Clearly explains  dimensionality  reduction

techniques used  and the rationale  for these. Shows  excellent insight

into dimensionality reduction.

 

Machine

Learning (10  marks)

Inappropriate

algorithms or

hyperparameters are chosen, or

explanations are  missing.

Basic algorithms  are chosen, but  their suitability and hyperparameters  are inadequately  explained.

Appropriate

algorithms are

selected,

relevance to the  task is justified  with reasonable  hyperparameters.

Algorithms are  well-suited to the  task, and

hyperparameters  are carefully tuned with clear

reasoning.

Algorithm

selection and

hyperparameter  tuning are

exceptional,

showing deep

understanding of  model choices.

Models (10

marks)

No model results  provided or results  do not address the  problem.

Basic model

results are

mentioned but  lack context or  interpretation.

Provides some  meaningful

insights, and

results are

described clearly.

Model outcomes  are explained with  insight, their

implications are  well interpreted.

Model

performance is  explained clearly,  interpretation

shows deep

understanding.

Orange /

AutoML

techniques (15  marks)

Machine learning  project is

disorganised and  difficult to follow.

Machine learning  project achieves  goals but with little organisation.

Machine learning  project is

somewhat

organised but

contains one or  more errors in the  workflow.

Machine learning  project is well

organised and  easy to follow.

Machine learning  project is

exceptionally

organised with a  logical workflow.

Clarity and

Presentation  (15 marks)

Answers are

unclear,

disorganised, and  difficult to

understand.

Answers are

somewhat clear,  but lack

organisation.

Answers are

mostly clear and  organised.

Answers are clear  and organised.

Answers are clear  and organised,  easy to

understand, and  engaging or

insightful.

Assessment 4: Computer Vision Case Study

Due date:

Week 12

Group/individual:

Individual

Word count/Time provided:

2500 words (1500 words for report + 1000 words for  model)

Weighting:

25%

Unit Learning Outcomes:

ULO-1, ULO-2, ULO-3, ULO-4

Assessment 4 Detail

You will be provided with a number of image libraries. You will choose one image library and  submit a report that outlines:

● A problem that could be solved with the image dataset

● How AutoML tools may help to analyse the imagery

● A strategy to solve the problem with the image library and an appropriate machine  learning model

You will also submit one or more models that you have trained. You are required to submit:

1. A document (2000 words) that includes:

○ A realistic fictional scenario in which the image library could help solve a problem

○ An outline of a strategic approach to solving the problem with the use of the image  library and a machine learning model trained from it

○ Explorations and insights gained from the image library

○ Image preprocessing used on the data, including any advanced pre-processing that  might be conducted with access to advanced AutoML tools

○ An evaluation of the performance of any models

2. The project used to develop your model(s).

3. The deployed model(s).

Assessments 4 Marking Criteria and Rubric

The assessment will be marked out of 100 and will be weighted 25% of the total unit mark.

Marking

Criteria

Not satisfactory (0- 49%) of the criterion  mark

Satisfactory

(50-64%) of the  criterion mark

Good

(65-74%) of the  criterion mark

Very Good

(75-84%) of the  criterion mark

Excellent

(85-100%) of the  criterion mark

Strategic

Problem

Solving (20

marks)

No relevant scenario or problem domain  is identified. No  relevant machine  learning objective is  identified or

explained.

Some

identification of  the scenario and  problem domain.  An objective of the machine learning  project is

identified, but not  explained.

Adequate

explanation of the  scenario and

problem domain.  An objective of the machine learning  project is

identified, but may not be well

Good explanation  of the scenario  and problem

domain. An

appropriate

machine learning  project objective is identified and

explained.

Excellent

explanation of the  scenario and

problem domain,  and the objective  of the machine  learning project.

explained.

Data (20

marks)

Does not explain  how the image

library connects to  the machine learning objective.

Able to somewhat  explain the

connection

between the

image library and  the objective of  the machine

learning project,  but no mention of  how further data  should be

collected or

augmented.

Able to somewhat  explain the

connection

between the

image library and  the objective of the machine learning  project. Shows  little knowledge of  how further data  should be

collected or

augmented.

Able to explain the connection

between the

image library and  the objective of  the machine

learning project.  Shows some

knowledge of how further data

should be

collected or

augmented.

Able to clearly  explain the

connection

between the

image library and  the objective of  the machine

learning project.  Shows great

insight into how  further data

should be

collected or

augmented.

Image

Processing (20  marks)

No image pre

processing is

performed.

Basic image pre processing is

performed, but  with no

explanation.

Image pre

processing is

mostly appropriate to the task, but  with little

explanation. More  advanced image  pre-processing is  mentioned but not  explained.

Image pre

processing is

performed and  adequately

explained. More  advanced image  pre-processing is  adequately

explained in

relation to AutoML tools.

Image pre

processing is

completely

appropriate and  clearly explained,  showing deep

understanding of  its role in image  analysis. More  advanced image  pre-processing is  clearly explained  in relation to

AutoML tools.

Models (10

marks)

No model results  provided or results  do not address the  problem.

Basic model

results are

mentioned but  lack context or  interpretation.

Provides some  meaningful

insights, and

results are

described clearly.

Model outcomes  are explained with  insight, their

implications are  well interpreted.

Model

performance is  explained clearly,  interpretation

shows deep

understanding.

Orange /

AutoML

techniques (15  marks)

Machine learning  project is

disorganised and  difficult to follow.

Machine learning  project achieves  goals but with little organisation.

Machine learning  project is

somewhat

organised but

contains one or  more errors in the  workflow.

Machine learning  project is well

organised and  easy to follow.

Machine learning  project is

exceptionally

organised with a  logical workflow.

Clarity and

Presentation  (15 marks)

Answers are

unclear,

disorganised, and  difficult to

understand.

Answers are

somewhat clear,  but lack

organisation.

Answers are

mostly clear and  organised.

Answers are clear  and organised.

Answers are clear  and organised,  easy to

understand, and  engaging or

insightful.