FIT5145: Foundations of Data Science

Assignments 1 & 3: Business and Data Case Study

Semester 1, 2025

1. Assignment 1 (Proposal): Draft a proposal to introduce a data science project of interest. The due date of Assignment 1 is: Friday, 4 April 2025, 11:55 PM (Week 5).

2. Assignment 3 (Report+Presentation): Write a comprehensive report on your data science project and prepare  a 4-minute presentation  on your project. The due date of Assignment  3 (the final project report and presentation slides) is: Friday, 23 May 2025, 11:55 PM (Week 11) and the presentation will be held in the Week 12 applied class.

-     Both Assignment 1 and 3 are individual assignments.

- Please do NOT zip your submission files. Zip file submission will have a penalty of 20% of the total mark of the assignment.

Focus of the Project Proposal

Assignments 1 and 3 require you to develop a novel data science project proposal that introduces an original approach to solving a significant real-world problem using data science methods.  You  are expected to go beyond existing studies by identifying unique problem statements, proposing innovative methodologies, or applying data science techniques in new contexts. Your proposal should demonstrate your ability to define a novel and important problem, identify relevant datasets, select appropriate methodologies, and develop effective evaluation strategies. The proposed project should align with the following business scenarios: agriculture, education, finance, gaming industry, healthcare, social media, and sports. You are encouraged to discuss any project ideas with your tutors for further guidance.

Assignment 1: Proposal (15%)

Weight: 15% of the unit mark

Submission format: one PDF file

Size: up to 1000 words.

What you need to do:

● Choose a data science project.

●    Write the  initial three sections: (1) Introduction; (2) Related  Work; and (3) Business Model (References as well to support your project) of the report, as detailed in the specification of Assignment 3: Report + Feedback + Presentation below.

We have developed a system named FLoRA to support you to accomplish Assignment 1, which you may access via: https://www.floraengine.org/moodle/my/courses.php.  You are expected to work with the chatbot embedded in FLoRA, powered by  cutting-edge Generative Artificial Intelligence  (GenAI) technology GPT-4o, to identify a novel and important problem to tackle in your data science project. You can discuss the assignment requirements with the GenAI-powered chatbot, seek suggestions for potential project topics in a specific domain, and gather information relevant to a specific project topic by conversing with the chatbot.  Even more, you may send the proposal draft to the chatbot and seek feedback for further improvement.

Please notice:

● We will send you the login credentials via emails for you to access the FLoRA platform.

●    You are only expected to use FLoRA to accomplish Assignment 1, though you may use it for Assignment 3 as well, it is not mandatory.

●    The conversational data you generate when interacting with the GenAI-powered chatbot will be used for textual analysis in Assignment 4 in this unit. That is, the conversational data will be shared with the whole class. Therefore, please notice the following:

○    Please only discuss your data science project with the GenAI-powered chatbot in English and do not ask any questions that are irrelevant to your project;

○    Please do not disclose any personal or sensitive information when interacting with the GenAI-powered chatbot.

○    There  are four  modules in  FLoRA  and  you  are  required  to  complete  all  of them.

Important: Any    incomplete   activities    in    these    modules   will   result    in   your conversational data with the chatbot being excluded from the dataset used for Assignment 4, preventing youfrom answering the questions in Assignment 4.

After logging to the platform, you will see there are four modules required to accomplish Assignment 1, as shown below:

Module 1: Pre-task activity

●    Please provide information about yourself as well as your prior knowledge and experience in data science and GenAI.

Module 2: Training Module

● We provide a set of tutorial documents to help you familiarise with FLoRA, including:

。 The system interface;

○ The annotation tool,  which you  can use to make annotation to the reading materials provide to help you get some inspirations about potential project ideas before discussing with the GenAI-empowered chatbot;

○ The essay writing tool, which you can use to draft the assignment;

○ The GenAI-empowered chatbot, which you can consult for help when solving  the assignment. The Chatbot uses the GPT-4o model.

●    Please notice that  all  these tools have been enabled in Module 2 (available on the top right corner) and you may familiarise yourself with these tools first before moving to Module 3 to start working on the assignment.

Module 3: Task - Assignment

●    This is the main module in which you are expected to accomplish Assignment 1.  Before discussing with the GenAI-powered chatbot, please first have a look at the “inspiring” materials that may give you some initial ideas of what data science can achieve in the domains where data science is playing an increasingly important role:

○ Data Science in Agriculture

○ Data Science in Education

○ Data Science in Finance

○ Data Science in Gaming Industry

○ Data Science in Healthcare

○ Data Science in Social Media

○ Data Science in Sports

You may use the provided annotation tool to annotate the useful information in these materials.

●    After selecting the domain that you would like to work on, use the GenAI-powered chatbot to get necessary help for accomplishing the assignment (e.g., seeking relevant information about a specific topic in the selected domain).

●    After you finish the draft, please (i) click the “Save Essay” button to send your submission to FLoRA; and (ii) copy your project text and paste it into a word processing tool (e.g., Microsoft Word), format it if necessary, and then  save it as a PDF file and submit it on Moodle as well.

Important: Please ensure that the final project text saved/submitted in FLoRA matches the PDF version submitted on Moodle, as the FLoRA submission will be used forpeer grading, as detailed later. You may save/submit the written report multiple times, and the final version saved/submitted will be exported forpeer grading.

●    Please notice that the conversational data you generate with the GenAI-powered chatbot will be used and shared for Assignment 4 and thus do not disclose any personal or sensitive information to the chatbot.

●    As we will use the  conversational  data for Assignment 4, ideally you have one “meaningful” discussion session with the GenAI-powered chatbot (instead of having multiple at different times)  in  Module  3  to  get  the  help  you  need  to  accomplish  Assignment  1.  Prior  to  this,  you  may  familiarise yourself with the chatbot (and other tools as well) in Module 2.

Module 4: Post-Task Activity

●    Please share your experience in using FloRA as well as the GenAI-powered chatbot to tackle Assignment  1. Your responses to these survey questions will be mandatory for including your conversational data to prepare an anonymised conversational dataset for Assignment 4.

For any technical issues in using FLoRA, please contact [email protected] and [email protected]

Assignment 3: Report (15%) + Feedback (5%) + Presentation (10%)

1. Assignment 3: Report

Weight: 15% of the unit mark

Submission  format: one  PDF  file  and  one  RMD  file  (for  demonstration  in  the  Characterising  and Analysing Data section)

Size: up to 2500 words

This report is your comprehensive analysis of how data science can be used to help solve a significant real-world problem. Please  answer the  following question in the FIRST page of your Assignment  3 submission:

●    Have  you  selected  a  topic  for  Assignment  3  that  is  different  from  the  one that you used for Assignment 1 (i.e., have you rewrote the first three sections of the report)?

Your report should have the following sections:

1. Introduction

○ Clear articulation of the specific problem the project aims to solve.

○ Background and context of the problem.

○ Importance of the problem (why it matters).

○ Specific goals of the project.

2. Related Work

○ Summary of existing research, projects, or industry solutions related to the problem.

○ Identification of gaps in current approaches.

○    Why or how your project should be considered as novel.

3. Business Model

○ Analysis about the business/application area the project sits in.

○ What kind of benefits or values the project can create for the specific business area?

○ Who are the primary stakeholders and how will they benefit from the project?

4. Characterising and Analysing Data:

○    Discuss potential data sources and analyze their characteristics (e.g., the 4 V's), evaluate the required platforms, software, and tools for data processing and storage based on the specific characteristics of the data or consider potential options (e.g., platforms, software, and tools) if your project expands in the future.

○    Specify the data analysis techniques and statistical methods (e.g., decision tree or regression tree) applicable to the project. Provide a rationale for the selected methods and discuss the expected  high-level  outcomes.  Note:  The  specification  of  data  analysis  and  statistical methods  should  be  different  from  the   demonstration  below   and  must  be   described separately.

。 Demonstration: identify a usable dataset for the proposed project and perform some basic analysis on the identified dataset to demonstrate the feasibility of the project, using R (e.g., detailing the information/features contained in the dataset, analyse the basic characteristics of the dataset, etc.), and report the analysis process and result in the demonstration section of a final report.

Note: Please include a link to download the dataset in the final report, and upload the R markdown file created for data analysis on Moodle.

5. Standard for Data Science Process, Data Governance and Management

。 Describe any standards used in your data science process

。 Describe  any  practices  for data governance and management in the project, e.g., how to address  key  issues  such  as  data  accessibility,  security,  and  confidentiality,  as  well  as potential ethical concerns related to data usage.

The sections would present aspects of Weeks 1-10 of the unit for your chosen case study.

The maximum word limit for the report (Assignment 3) is 2500 words.  It may include some/all ofyour Assignment  1, modified if needed (counted in the 2500 word total). References at the end of the report (i.e., URLs and academic publications) are not included in the word count. Note that staying within the word limit demonstrates your ability to write concisely.

2. Assignment 3: Feedback from Assignment 1

Weight: 5% of the unit mark

Please ensure the following content is included on the SECOND page of your Assignment 3 submission.:

●   What feedback did your tutor provide for Assignment 1?

●   Briefly describe how you incorporated this feedback to improve your Assignment 3 submission (maximum 150 words).

3. Assignment 3: Presentation (Slides + Verbal) + Peer-review Evaluation

Weight: 10% of the unit mark

Submission format: one PDF file (Slides)

Size: a maximum of 10 slides (Slides)

You need to submit your presentation slides along with your final report. The 4 minute presentation is given in Week 12 during your assigned applied class and after your presentation, the tutor will ask at least one question to the presenter (1 minute). You will also be required to review and provide feedback on presentations of other students (peer-review) during the applied class in Week 12, using the Google Form. provided.

How you will be assessed

See the marking rubric to understand how we will grade your assignments.

To introduce you to various important and novel project ideas developed by your peers and ensure a more accurate and fair assessment of your assignments, we will conduct peer grading for different parts of the assignments, as outlined below.

Assignment  1  proposal: The  15%  awarded  for  your proposal is broken down into the following categories:

● Problem Clarity (2%): Is the problem well-articulated and clearly defined?

● Business Model Analysis (2%): Is the role of data in the project clearly articulated in relation to the business model? Are the benefits and value of the project clearly outlined? Are the primary stakeholders identified and their needs addressed?

● Problem Importance (4%): Does the project have real-world applications? Does it address key  social,  environmental, or business challenges and demonstrate potential for significant social impact?

● Novelty (4%): Does the project address an important and novel problem? Does it introduce a new or unconventional approach? Does it tackle an underexplored or emerging issue in data science?

● Peer grading (3%): You will review 6 randomly selected Assignment  1 submissions from other students and rate them based on Problem Importance and Novelty. Your peer-grading mark (3%) will be awarded in proportion to the number of reviews completed. Completing all 6 reviews will earn the full 3%. The peer-graded scores for Problem Importance and Novelty will be averaged and combined with the tutor’s evaluation score to determine the final score for these aspects of a project. The average peer-graded score and the tutor-assigned score will each contribute equally to the final score. Important: Please ensure that the final project text saved/submitted in FLoRA matches the PDF version submitted on Moodle, as the FLoRA submission will be used forpeer grading, as detailed later. You may save/submit the written report multiple times, and the final version saved/submitted will be exported forpeer grading.

Please ensure that

Assignment 3 report:  You will be assessed on your ability to:

●    define  the  problem,  provide  background  and  significance,  outline  specific goals,  analyze  the business domain and its value creation, identify key stakeholders and their benefits, summarize existing  research  or  industry  solutions,  highlight  gaps  in  current  approaches,  and justify  the project's novelty  and potential  impact  (You  can  reuse  the  content  from  Assignment  1 for this section);

●    discuss potential data sources and analyze their characteristics (e.g., the 4 V's) and evaluate the required  platforms,  software,  and  tools  for  data  processing  and  storage  based  on  the  specific characteristics of the data or consider potential options (e.g., platforms, software, and tools) if your project expands in the future;

●    specify the data analysis techniques and statistical methods (e.g., decision tree or regression tree) applicable to the project. Provide a rationale for the selected methods and discuss the expected high-level outcomes;

●    identify a usable dataset for the proposed project and perform. some basic analysis on the identified dataset to demonstrate the feasibility of the project, using R (e.g., detailing the information/features contained  in  the  dataset,  analyse  the  basic  characteristics  of the  dataset,  etc.),  and  report  the analysis process and result in the demonstration section of a final report;

●    describe any standards used in your data science process and practices for data governance and management in the project, e.g., how to address key issues such as data accessibility, security, and confidentiality, as well as potential ethical concerns related to data usage;

● think critically and creatively, providing justification and analysis;

● provide a good quality of report in terms of structure, expression, grammar and spelling.

For both assignments, make sure that any resources you use are acknowledged in your report. You may need to review the FIT citation style to make yourself familiar with appropriate citing and referencing for this assessment. Also, review the demystifying citing and referencing guide for help.

Please also make sure that the Turnitin scores will be generated properly for your submissions. If a submission receives a high Turnitin score (e.g., more than 15%), the student will likely need to provide further explanation on the project idea and a penalty might be imposed on the submission in case no proper justification is provided.

If you  use  GenAI  for  this   assignment  (except  for  discussing  potential  project  ideas  with  the GenAI-powered chatbot in FLoRA or seeking feedback from the chatbot), you must clearly document the type of GenAI used, how it contributed to the assessment, and provide a written acknowledgment of its use and extent in the final report.

Assignment 3 Presentation (Slides + Verbal Presentation + Peer-Review Evaluation): The 10% awarded is broken down into the following categories:

● Presentation (Slides) – 2% (evaluated by your tutor);

● Presentation (Verbal Presentation) – 3% (evaluated by your tutor);

●   Peer-Review Evaluation – 5% (average scores given by your peers in the same applied class during Week  12). You may only evaluate projects from other students in your class and are not allowed to evaluate your own project.

What you need to do

Before you begin, make sure you:

●    You are highly recommended to review the “inspiring” materials provided in FLoRA to select a topic that you would like to work on. Also, you are highly recommended to propose your own interesting and novel topic and please feel free to discuss it with your tutors to ensure the topic is suitable.

●    Download the marking rubric (available on Moodle) as guidance on how you will be assessed. Choose a data science project topic, and then:

1. Do preliminary research about your project topic and the relevant technologies by conversing with the GenAI-powered chatbot

2. Write and submit your proposal with cited references (Assignment 1)

3. Research and prepare your final report with cited references.

4. Submit your report and do a presentation (Assignment 3).

You are free to modify the initial proposal sections submitted for Assignment 1 (especially in response to feedback from your marker), or even change topics, when you are working on Assignment 3.

How to Submit

Once you have completed your work, take the following steps to submit your work. Penalties may be applied to your marks if the following instructions are not followed.

1.   For Assignment 1, please finish and save the project proposal first in FLoRA, copy & paste it into a word processing tool (e.g., Microsoft Word) for the purposes of structuring/formatting, then save the project proposal in the PDF format and submit it on Moodle.

2.   Please  ensure  you name  the  file  containing  your  proposal/report/slides correctly  using the following format:

FirstName_StudentNumber_AssignmentNumber(_report or _slides).pdf

e.g., Guanliang_12345678_Assignment1.pdf or

Guanliang_12345678_Assignment3_report.pdf or

Guanliang_12345678_Assignment3_slides.pdf

3.   Upload your assignment file in the corresponding assignment link provided on Moodle.