DTS001 Data Analytic for Entrepreneurship

Final Coursework

Submission deadline: 4^th Nov.

Percentage in final mark: 100%

Learning outcomes assessed:

A: Preprocess, analyse and interpret data using a modern computer package

B: Summarize and visualize data using a modern computer package

C: Present findings to a business audience in a suitable format

Late policy: 5% of the total marks available for the assessment shall be deducted from the assessment mark for each working day after the submission date, up to a maximum of five working days

Risks:

Please read the coursework instructions and requirements carefully. Not following these instructions and requirements may result in loss of marks.

Plagiarism results in award of ZERO mark.

The formal procedure for submitting coursework at XJTLU is strictly followed. Submission link on Learning Mall will be provided in due course. The submission timestamp on Learning Mall will be used to check late submission.

All students must download their file and check that it is viewable after submission. Documents may become corrupted during the uploading process (e.g. due to slow internet connections). However, students themselves are responsible for submitting a functional and correct file for assessments.

All submissions must be written in English; Any parts containing Chinese will not be considered for marking.

Overview

In this coursework, you are required to complete two tasks based on the given dataset and submit a compressed document (in .zip file) that includes two files:

1. Task1: An Excel file (in .xlsx file) containing your visualization and modeling process and results for the given dataset. If your name is Alan Turing and your ID is 1234567, this file should be called 1234567 Alan Turing Task1.xlsx

2. Task2: A report (in .pdf file) analyzing the visualization and modeling results. If your name is Alan Turing and your ID is 1234567, this file should be called 1234567 Alan Turing Task2.pdf

The assignment must be submitted via Learning Mall Online to the correct drop box. Only electronic submission is accepted and no hard copy submission.

Task 1 (50 marks)

You are given a dataset of Wine Quality of Vinho Verde. This dataset includes the comprehensive quality of taste and aroma (hereinafter referred to as "quality") given by authoritative experts, as well as the chemical analysis results of these wines. You need to design and create your visualization and model based on the dataset. The visualization will show the impact of different chemical analysis results on the wine quality (which is in the column in red bond font in the .xlsx file), while the model needs to consider multiple chemical analysis results to predict the wine quality. Here are task specifications:

Target for visualization: You are asked to use excel to create a visualization that complete the following tasks

O Clean and preprocess the original dataset (9 marks)

O Show the impact of the citric acid on the wine quality through appropriate tables and charts (5 marks)

O Show the impact of the volatile acidity on the wine quality through appropriate tables and charts(5 marks)

O Show the impact of the sulphate on the wine quality through appropriate tables and charts (5 marks)

O Show the impact of the residual sugar on the wine quality through appropriate tables and charts (5 marks)

Target for model: You are asked to use excel to construct a model that can predict the wine quality (which is in the column in red bond font in the .xlsx file) based on the different chemical analysis results of these wines. Your model needs to complete the following tasks.

o Choose the appropriate independent variable for the appropriate model (8 marks)

o Strive for low Mean Square Error (MSE) as much as possible (8 marks)

o Use the trained model to output the predicted wine quality, and present a table showing the Mean Squared Error (MSE) corresponding to different predicted value ranges (5 marks)

The submitted Excel file should include:

o The original dataset

o The dataset after data preprocessing

o All visualized tables and charts

o Summary output of the constructed model

Detailed Requirements:

o The formulas and functions used in data preprocessing needs to be retained in your xlsx file. You need to demonstrate through formulas how the processed data was transformed step by step.

o Visual charts and tables need to be generated by Excel and remain in an editable state in your xlsx file. Screenshots will not be accepted.

Additional notes:

o The use of add-ins that have not been mentioned in lecture is allowed, but it is necessary to refer the source and ensure that the add-ins is publicly available

o It is allowed to use newly constructed features during the model constructing, but these features must be based on the original dataset, and the process of constructing the new features needs to be retained.