5500 words (A) Data Analysis Identify the current issues in the use of Big Data Analytics in the fashion retail industry.
Budget: $2 – $8 USD
Brief
This assignment is divided into two sections
Given a dataset/s, the students are required to analyse dataset. The students should clearly mention all
the steps undertaken from importing data, cleaning, preparing data, and analysing data. The students
should provide appropriate visualisation/s and report the results of analysis. All the steps/Python
code/results must be shared.
(A) Data Analysis (75%)
• On given datasets, identify the questions that you would like to answer through data
analysis.
• Given two datasets, use SQL queries to create a new dataset for analysis.
• Perform data cleaning and pre-processing tasks on the new dataset.
• Use HIVE, MapReduce (or Spark) and machine learning techniques to analyse data.
• Perform visualization using Python and PowerBI and report the results.
(B) Issues and Solution (25%)• Identify the current issues in the use of Big Data Analytics in the fashion retail industry.
Based on the identified issues, propose an effective solution using various technologies.
Your report should be produced in a professional report style and should contain at least 5500 words
excluding the references and appendices sections. This is an individual piece of work and is worth 75% of
the module mark. The file name should be saved as DAT7015_2_Student-number. The student may be
asked to present or reflect on the submitted report.
All the students have to give the presentation based on their assignment. It is mandatory for all the
students to present. The students who do not appear for the presentation will be considered as FAIL.
This assignment is divided into two sections
Given a dataset/s, the students are required to analyse dataset. The students should clearly mention all
the steps undertaken from importing data, cleaning, preparing data, and analysing data. The students
should provide appropriate visualisation/s and report the results of analysis. All the steps/Python
code/results must be shared.
(A) Data Analysis (75%)
• On given datasets, identify the questions that you would like to answer through data
analysis.
• Given two datasets, use SQL queries to create a new dataset for analysis.
• Perform data cleaning and pre-processing tasks on the new dataset.
• Use HIVE, MapReduce (or Spark) and machine learning techniques to analyse data.
• Perform visualization using Python and PowerBI and report the results.
(B) Issues and Solution (25%)• Identify the current issues in the use of Big Data Analytics in the fashion retail industry.
Based on the identified issues, propose an effective solution using various technologies.
Your report should be produced in a professional report style and should contain at least 5500 words
excluding the references and appendices sections. This is an individual piece of work and is worth 75% of
the module mark. The file name should be saved as DAT7015_2_Student-number. The student may be
asked to present or reflect on the submitted report.
All the students have to give the presentation based on their assignment. It is mandatory for all the
students to present. The students who do not appear for the presentation will be considered as FAIL.