Overview
Students are required to submit a report of approximately 2500 words along with exhibits to support findings with respect to the provided Loan Prediction Problem dataset. This report should consist of a comprehensive review of data quality issues, detailed descriptions of data cleaning techniques, and an in-depth theoretical discussion on data preprocessing. Additionally, students are required to present their work in class during week 12 in a 10-minute presentation.
Introduction:
Financial institutions rely heavily on accurate data to assess loan applications and minimize credit risk. In this assignment, students will theoretically analyze the Loan Prediction Problem dataset (download from Moodle) to identify data quality issues and prepare it for further analysis. This includes detecting and handling missing values, outliers, noise, and duplicate entries to ensure the dataset is clean and reliable for predictive modelling.
Tasks for the Report:
Task 1: Identify Common Data Quality Issues (10 marks)
- Identify and explain four common data quality issues present in the dataset that require cleaning.
- Discuss how each issue can impact data analysis and decision-making processes.
TEQSA: PRV14311
CRICOS: 03836J
Australia Advance Education Group Pty Ltd. trading as Sydney International School of Technology and Commerce
ABN 74 613 055 440 | ACN 613 055 440
Level 14/233 Castlereagh Street, Sydney NSW 2000
Page | 2
Task 2: Describe Data Cleaning Techniques (8 marks)
- Identify and describe four common techniques used for data cleaning, including handling missing values, handling outliers, dealing with inconsistencies, and removing duplicates.
- Provide theoretical examples of how these techniques can be applied to Loan Prediction Problem Dataset.
Task 3: Data Pre-processing (10 marks)
Perform data pre-processing to prepare the dataset for analysis. This includes selecting relevant columns, cleaning the dataset by removing irrelevant information, handling missing values, and transforming data formats. Students must do the pre-processing phase in Excel. They are required to provide an explanation of the pre-processed data and upload it to Moodle.
References (2 marks)
This unit requires you to use APA system of referencing. See Sydney International’s quick reference guide. It should be used in conjunction with the online tool Academic Writer: https://extras.apa.org/apastyle/basics-7e/#/. All academic references should be in APA reference style.
-Include the DOI or URL for all the references to provide a complete and accessible reference. If a DOI is available, it should always be used in references. If no, a URL or other access information should be included.
- Include proper in-text citations for all the sources you reference in your assignment.
Report Structure:
Cover Sheet
Title Page
Table of Contents
Common Data Quality Issues (10 marks)
Data Cleaning Techniques (8 marks)
Data Pre-processing (10 marks)
References (2 marks)
TEQSA: PRV14311
CRICOS: 03836J
Australia Advance Education Group Pty Ltd. trading as Sydney International School of Technology and Commerce
ABN 74 613 055 440 | ACN 613 055 440
Level 14/233 Castlereagh Street, Sydney NSW 2000
Page | 3
Report (30 marks): Expected word count 2,500 words Students are expected to submit their assessments via Turnitin on Moodle. Due date for submission of Group Report is week 11- 8th of Feb.
Presentation (10 marks): 10-minute group presentation delivered in-class on week 12.
This assignment has a 5-day cutoff period. A 10% penalty per day (from the total marks) applies for each day when the submission is late. Submission will not be accepted after 5-day cutoff period.
Marking Criteria
Refer to the following marking guide.
Identify Common Data Quality Issues (10 marks)
Accurate identification of four data quality issues and comprehensive explanation of how each issue can impact data analysis.
(10 marks)
Accurate identification of three data quality issues and detailed explanation of how each issue can impact data analysis.
(8 marks)
Accurate identification of two data quality issues and clear explanation of how each issue can impact data analysis.
(6 marks)
Incomplete identification of data quality issues and/or no explanation of impact.
(3 marks)
No Submission
(0 mark)
Describe Data Cleaning Techniques (8 marks)
Correctly identifies and provides clear, thorough, and comprehensive explanations for each of the four common data cleaning techniques demonstrating exceptional understanding of their purpose and application.
(8 marks)
Identifies three or four common data cleaning techniques with adequate descriptions demonstrating understanding of their purpose and application.
(6 marks)
Identifies two common data cleaning techniques with brief or vague descriptions lacking clarity.
(4 marks)
Identifies one or two data cleaning techniques but with inaccurate descriptions or lacks clarity and understanding
(2 marks)
No submission
(0 mark)
TEQSA: PRV14311
CRICOS: 03836J
Australia Advance Education Group Pty Ltd. trading as Sydney International School of Technology and Commerce
ABN 74 613 055 440 | ACN 613 055 440
Level 14/233 Castlereagh Street, Sydney NSW 2000
Page | 4
Data Pre-processing (10 marks)
Comprehensive data pre-processing with accurate selection of relevant columns, removal of irrelevant information, handling of missing values, and transformation of data formats, along with thorough explanations.
(10 marks)
Detailed data pre-processing with accurate selection of relevant columns, removal of irrelevant information, handling of missing values, and transformation of data formats, with clear explanations.
(8 marks)
Adequate data pre-processing with selection of relevant columns, removal of irrelevant information, handling of missing values, and transformation of data formats, with some explanations.
(6 marks)
Partial data pre-processing with minor errors in selection of relevant columns, removal of irrelevant information, handling of missing values, and transformation of data formats, with limited explanations.
(3 marks)
No Submission
(0 mark)
APA Referencing (2 marks)
Perfect APA style; all sources correctly cited, including DOI or URLs, and working links.
(2 marks)
Minor errors in APA style, all sources cited, DOI or URLs provided.
(1.5 marks)
Some formatting errors, most sources included, partial DOI or URLs.
(1 marks)
Many formatting errors, some missing sources, limited detail, no DOI or URLs.
(0.5 marks)
No Submission
(0 mark)
Presentation (10 marks)
Clear, engaging, and comprehensive presentation with thorough coverage of key findings and theoretical insights, delivered within the time limit.
(10 marks)
Clear and comprehensive presentation with coverage of key findings and theoretical insights, delivered within the time limit.
(8 marks)
Adequate presentation with coverage of key findings and theoretical insights, with minor time management issues.
(6 marks)
Partial presentation with limited coverage of key findings and.
(3 marks)
No Submission
(0 mark)