ASSESSMENT TASK TEMPLATE
Module Code: BMD0007
Module Title: DATA ANALYSIS AND VISUALISATION
Assessment Task(s) 2500 words individual data analytic report
Academic Year 2019-20
Learning Outcomes [Module Leader to insert ONLY learning outcomes that apply to this assessment task. These can be found on the Module Specification Document.]
This assessment task addresses the following learning outcomes from the module specification
1. Demonstrate a conceptual and critical understanding of contemporary data analysis theory.
2. Demonstrate conceptual understanding of visualisation techniques to communicate data analysis to different audiences.
3. Formulate, justify and defend an appropriate methodology for the interrogation, utilisation and presentation of data.
4. Express and justify an individual perspective in the field of Data Science, with a particular focus on scenarios in which there is an opportunity to utilise data.
5. Utilise a range of software and datasets to develop and operationalise an appropriate methodology for the investigation of a problem in the field of Data Analysis.
Assessment brief [Module Leader should insert formal statement of the assessment task brief]
2500 words individual data analytic report (100%)
For this assignment you will need to complete the following 2 tasks and produce an analytical report, supported by data (max 1700 words for Task 1, max 800 words for Task 2, and max 2500 words for total).
Task 1 (70%):
There are two cases in this task. If your Student Number is odd, you should complete Case 1. If your Student Number is even, you should complete Case 2.
Case 1: Advertising on Facebook
Huddersfield Analytic (HA) is a data consultancy agency who offer data analysis, statistical decision making, data designs, data cleansing as part of their services. Digital History (DH) is a social media marketing company which provides services on various platforms such as Facebook, Twitter, Instagram and more. It is evident that as companies start to migrate online social media is a key tool in helping organisations to communicate and influence their customers for leveraging their business.
DH has approached HA with a view to analyse its marketing performance on one of their key platforms namely Facebook. DH requires a comprehensive analytic report to guide its marketing decision making on Facebook (e.g., what are the key influencing factors of Facebook advertising? How to improve the impact of advertising campaign on Facebook? …) In order to achieve this DH have provided you with a dataset, which you are required to analyse.
The given dataset (dataset_Facebook.csv) contains all the posts published between the 1st of January and the 31th of December of 2014 on the Facebook’s page of DH. There are 790 posts published in total and each post is described by 19 variables. The variables are listed by the following table.
Variable Description
Post Month 1 = January, 2 = February, …, 12 = December
Post Weekday 1 = Sunday, 2 = Monday, …, 7 = Saturday
Day of Year 1 = 01/01/2014
Post Hour 0, 1, 2, …, 23 (24 hours)
Type Type of content (Photo, Video, Status, Link)
Category 1 = action (special offers and contest), 2 = product (direct advertisement, explicit brand content), 3 = inspiration (non-explicit brand related content).
Paid If the company paid to Facebook for advertising, 1 = yes, 0 = no
Page total likes The number of likes the page had when the post was published. (Cumulative/Aggregate value)
Lifetime Post Total Reach The number of people who saw a page post (unique users).
Lifetime Post Total Impressions Impressions are the number of times a post from a page is displayed, whether the post is clicked or not. People may see multiple impressions of the same post. For example, someone might see a Page update in News
Feed once, and then a second time if a friend shares it.
Lifetime Engaged Users The number of people who clicked anywhere in a post (unique users).
Lifetime Post Consumers The number of people who clicked anywhere in a post, excluding liking a comment, liking a reply to a comment, etc.
Lifetime Post Consumptions The number of clicks anywhere in a post.
Lifetime Post Impressions by people who have liked your Page Total number of impressions just from people who have liked a page.
Lifetime Post reach by people who like your Page The number of people who saw a page post because they have liked that page (unique users).
Lifetime People who have liked your Page and engaged with your post The number of people who have liked a Page and clicked anywhere in a post (Unique users).
Comment Number of comments on the publication.
Like Number of “Likes” on the publication.
Share Number of times the publication was shared.
Total Interactions The sum of “likes,” “comments,” and “shares” of the post.
More explanations please see:
http://www.agorapulse.com/blog/facebook-reach-metrics-ultimate-guide
https://www.facebook.com/help/274400362581037
Case 2: Mobile App Analysis
The emerging mobile internet, smart mobile devices, and related techniques have been disrupting the business world. Millions of mobile apps are developed and launched to the market. A new company, HudSoft, plans to enter this market, but the proper strategy of app development should be addressed evidently according to real market data.
A dataset (AppStore.csv) collected in July 2017 from the iOS app store through the iTunes Search API is provided to you. This dataset contains the details of more than 7000 iOS apps, which are described by 15 variables listed in the following table.
You are required to produce a comprehensive analytic report to support HudSoft’s decision-making on app development (e.g. what are the key features of top trending apps? How to get more people to download your app? …).
Variable Description
id App ID
track_name App Name
size_bytes Size (in Bytes)
Price(USD) Price amount
ratingcounttot User Rating counts (for all version)
ratingcountver User Rating counts (for current version)
user_rating Average User Rating value (for all version)
userratingver Average User Rating value (for current version)
ver Latest version code
cont_rating Content Rating
prime_genre Primary Genre
sup_devices.num Number of supporting devices
ipadSc_urls.num Number of screenshots showed for display
lang.num Number of supported languages
vpp_lic Vpp Device Based Licensing Enabled
To complete Task 1 (70%), you need to:
1. Introduce the meanings of variables with referring to related backgrounds (marketing, statistics, and any related area) clearly to the audiences, bearing in mind that the audiences do not have much experience with data. (15%)
2. Summarily describe the dataset by descriptive statistics (measures of centrality and dispersion) and charts (bar, pie, histogram, boxplot, etc.). Alongside this provide a clear and succinct interpretation of the data. (15%)
3. Mine the data through proper approaches (Chi-squared test and multiple regression analysis are required, and any other advanced analysis may be applied to reveal further information) to identify the relationships among the variables. (20%)
4. Provide evidence-based suggestions to your client according to the results of your analyses. (15%)
5. Present your report professionally and adhere to all referencing principles. (5%)
Task 2 (30%): Time series analysis.
To complete this task, you are required to analyse the daily stock price of a company listed by FTSE100 index from 01/01/2018 to 31/12/2019. The data can be downloaded from Yahoo Finance or Google Finance. The list of companies is provided by FTSE100.csv
The specific company you need to analyse depends on the last two digits of your student number. For example, if your student number is “U19XXX72”, your company is “No.72, CRDA.L, CRODA INTERNATIONAL PLC” (check FTSE100.csv).
You are required to decompose the time series, apply exponential smoothing (single, double, and Winter’s), and generate 20 forecasts for each exponential smoothing model. All of the analyses and plots should be generated by R.
You are advised to:
[Module leaders should complete this section to provide any task-specific guidance to completing the work. Some examples below for illustration. Refer for example, to any relevant formative feedback students might have had. The examples below are only indicative]
• Avoid description of the content of material referred to – critical Assessment is required where specified.
• Work should be referenced in APA 6th style. The link below is to the library guidance on referencing and it is recommended you use these resources to ensure your references are in the correct format.
•
• Read widely from textbooks, journals and authoritative commentaries in forming your views.
• Refer back to your tutorial work and notes where you have covered key issues and developed critical argument that is relevant to the requirement of this assessment.
• Pay close attention to the Assessment Criteria at the end of this document – this lists general assessment criteria and specific criteria to the requirements of this assignment. These criteria will be used to inform your electronic feedback on your marked assignment.
• Use the University Referencing guide which is APA 6th. Note that poorly referenced material will lose you marks (make sure you consult the Learning Development Group Tutors on level 1 of the Business School for any additional help needed). You can access APA 6th via Brightspace by clicking on the Library button to access the easy to use online guide.
• Do not exceed the word limit. A 5% mark penalty applies for work exceeding the word limit.
Marking criteria
1. Please refer to the assessment task-specific criteria in Appendix 1. These show you the issues that will guide your tutors in marking your work. You are encouraged to use these at all stages of preparing your work. Please remember that the marking process involves academic judgement and interpretation within the marking criteria.
2. In addition to the assessment task-specific criteria, generic assessment criteria are attached in Appendix 1 & 2.
3. The University has regulations relating to academic misconduct, including plagiarism. The Learning Development Group can also advise and help you about academic conventions and avoiding ‘poor scholarship’ which can result in potential academic misconduct.
Submission information [Module leader should complete as appropriate]
Word Limit: Maximum 2500 words
Submission Date:
Feedback Date:
Submission Time: 15.00
Submission Method:
Tutor Reassessment yes
Notes:
Please refer to the Module Handbook for Assessment Guidance in Section 5.
