Why this assignment?
• Opportunity to apply theory into practice
• Exposure to real-life scenario
• Develop meta-cognitive skills by reflecting on feedback
What are the types of skills that I will acquire upon completion of this assignment?
• Written communication skills
• Think critically and reflectively.
• Practical skills using Tableau and Excel
• Practical skills using Knime Analytics Platform
• Application knowledge in solving problems.
• Self-management skills.
Assessment Overview:
This assessment is designed to develop students’ skills in the co
ect usage of analytical techniques and interpreting data for making managerial decisions. The main task is to analyse business data and to prepare a report for management based on an analysis of the data. The focus is on understanding the use of data analytical tools in a business context and develop written communication skills.
2
Assignment-3 tasks and description Tasks
Steps/Description
Which tools to use to complete?
How to Submit your Work
Construct classification tool
Construct classification tool to effectively assist the buyer in identification of cars likely to be Kicks.
• Experiment different configurations of the decision tree tool in Knime to find the best one you can. (NB. The e
or rate should be less than 15%).
• It is expected that while exploring this tool, you may need to keep coming back to explore the dataset to find the best set of inputs for your classification problem#.
Use Knime software
Data file (Excel), Knime file (of your decision tree) on ePortfolio**
Create Dashboard
Create dashboard
• When you are happy with your classification tool, create a dashboard in Tableau or Excel to present these inputs and how they affect IsBadBuy (Kicks).
• Be mindful to choose appropriate visuals for your dashboard.
Use Tableau or Excel
Dashboard (Tableau or Excel) on ePortfolio**
Write a 1000-word report
What to include in report?
Once successfully creating a classification tool, describe the tool’s functionality with respect to input contributions to the Kick classification.
• Evaluate your classification tool and explain how it may assist the buyer to reduce the Kicks rate.
• Using the data analytic methods you have learnt in the whole semester, explain your analysis, interpretation in the experiment to support decision makers.
Use Word
Combine item 3 and 4 and submit it on Turnitin
Self-reflection on feedback from assignment-2
Reflection Proforma:
Use the reflection proforma included in this document to complete your self-reflection and attach it at the end of your report (item-3 above)
Use Word
Note:
# use Excel clean dataset and Data Dictionary from Assignment-2
**Refer to LEO on instructions on how to submit files on ePortfolio (Same process as assignment -2)
Refer to case study (page-6) – the same case study as before.
Refer to ru
ic for weight allocation and marking schema (Page-5 in this document)
Case Study: Don’t Get Kicked (Same as assignment-2)
One of the biggest challenges of an auto dealership purchasing a used car at an auto auction is the risk that the vehicle might have serious issues that prevent it from being sold to customers. The auto community calls these unfortunate purchases "kicks".
Kicked cars often result when there are tampered odometers, mechanical issues the dealer is not able to address, issues with getting the vehicle title from the seller, or some other unforeseen problem. Kicked cars can be very costly to dealers after transportation cost, throw-away repair work, and market losses in reselling the vehicle.
Data analysts who can figure out which cars have a higher risk of being kick can provide real value to dealerships trying to provide the best inventory selection possible to their customers.
The challenge of this case study is to predict if a car purchased at an Auction is a Kick (bad buy).
The data dictionary, Carvana_Data_Dictionary.txt, and the data files can be downloaded from LEO under Assessment tab. The data dictionary describes the 34 attributes: RefId, in the first column, contains the ID number for each record. IsBadBuy, in the second column, is the binary dependent variable, where a 1 (one) means “is Kick” and 0 (zero) “is not Kick”. The remaining columns (3 through 30) are independent variables. The dataset contains records for 72,561 vehicles, of which 12.3% are Kick. (Adapted from Kaggle competition)
Important notes for assignment 3
· 1000 word report writing
· Case scenario – same data set, data cleaning and data pre processing
· Individualisation – dashboard (multiple charts, either Excel or Tableau)
· Data classification tool – Knime software (understand from week 9 materials) free download
· Study Weeks 7-9 materials
· Reflection – last page of the assessment 3 specifications and must be included in the report
· Analyse the case study once again and find out multiple problems and problem causes
· How to submit – upload Excel or Tableau,Knime file, paste secret link into Word doc and upload into LEO. Same procedures from assignment 2
· Dashboard
· Contain relevant charts from Week 7
· Spreadsheet – data cleaning / pre processing
· Each image should have a caption
· Report – appropriate format
· Data analytical tools – Excel or Tableau
· Reflect from the beginning before questions
· Classification tool – experiment decision tree and e
or rate should be less than 15%.
· To calculate the kick rate for each chosen input, only use and show the decision tree in the Knime software.
· To calculate kick rate for auction field = Total no of kicks / Total no of cars (for each auction site)
· In report writing, must explain interpretation of Tableau/Excel sheet dashboard, how they a
ive at the input data file and interpretation of the outcome of the decision tree.
· Dashboard – must provide reasonable and sensible charts (multiple charts), that chart should show Kicks rate
· Knime decision tree – must have a working workflow with co
ect class column, class column of the tree learner should be is ‘bad buy’. Needs to be less than 15% (if 15-20% the marker will still accept it)
· Report writing – always write in 3rd person, avoid ‘I’, ‘we’, ‘she’ words etc. Provide good reasons of your choices in relation to data analysis (Wk 7) and data mining (Wk 7)
· Describe how data analysis you did and explain why?
· Must conclusion the report as a data analyst
· In Knime, you must check the confusion matrix in the scorer and try to improve the e
or rate
· Charts should help the decision marker with solving the problem
Report should contain: - in report, do introduction, theory component of the classification tool you've used, the analysis/interpretation of the classification tool and conclusion
Important notes:- Here I have attached Week7 to Week 9 files that will support for this assignment. Also here I have attached excel file for the calculations.
PPT_Template_16_9_2017
Office | Faculty | Department 1 |
Week 7
Data visualisation and
Reporting
DATA201
Data Analytics and
Decision Making
Prepared by Dr. Thuy-Linh Nguyen
ased on Sharda et al (2018)
Fast track your degree and study two units in
Rome:
20 January – 2 Fe
uary 2019*
BIPX202 Community Engagement:
Building Strengths and Capabilities
• Undertake an international
community engagement placement
BUSN304 Working with Diversity
and Conflict
• Learn about communicating
working internationally
Places on this program are strictly limited and will be allocated on a first come basis.
Total costs are anticipated to be approximately $2,600-$2,800 (tbc). Students may be eligible for
travel assistance via the Vice Chancellor & President Travel Grant ($500)
For more information on enrolment contact XXXXXXXXXX
* Course offerings are subjects to student numbers
mailto: XXXXXXXXXX
Office | Faculty | Department 3 |
Why are we doing this?
By completing the activities in this week you should be able to:
• Describe basic and specialised charts and graphs
• Evaluate different chart options and pick a suitable one for your need
• Explain what a dashboard is, its characteristics, and best dashboard practice
• Design and create a basic dashboard
• Explain the role of Business Reporting in managerial decision making
• Identify major types of Business Reporting
These weekly ILOs will help you achieve the unit ILO:
• LO3 Assess and schematize the technical issues present in the stages of a data analysis
task and the properties of different technologies and tools that can be used to deal with
the issues (GA4, GA5, GA8, GA10)
Office | Faculty | Department 4 |
Essential Question
What and how can I use data visualisation to effectively tell my story and
support managerial decision making?
4 |
Office | Faculty | Department 5 |
Data visualisation
Definition
• “The use of visual representations to explore, make sense of,
and communicate data.”
Data visualization vs. Information visualization
• Information = aggregation, summarization, and
contextualization of data
• Related to information graphics, scientific visualization, and
statistical graphics
• Often includes charts, graphs, illustrations, …
Office | Faculty | Department 6 |
A
ief history
• Data visualization can date back to the second century AD
• Most developments have occu
ed in the last two and a half
centuries
• Until recently it was not recognized as a discipline
• Today’s most popular visual forms date back a few centuries
Office | Faculty | Department 7 |
The first pie chart
Created by
William
Playfair in
1801; who is
widely
credited as
the inventor of
the modern
chart
Office | Faculty | Department 8 |
Decimation of Napoleon’s Army during the
1812 Russian Campaign
Created by
Charles
Joseph
Minard;
arguably the
most popular
multi-
dimensional
chart
Office | Faculty | Department 9 |
Basic charts and graphs
Office | Faculty | Department 10 |
Specialised charts and graphs
Office | Faculty | Department 11 |
Which
chart or
graph
should
you use?
Office | Faculty | Department 12 |
An example Gapminder chart –
Wealth and health of nations
See
Gapminder.org
for interesting
animated
examples.
https:
www.gapminder.org/tools/#$chart-type=bu
les
Office | Faculty | Department 13 |
The emergence of Data Visualisation and Visual
Analytics
• Magic Quadrant for Business
Intelligence and Analytics
platforms (Source:
Gartner.com)
• Tableau, Microsoft, Qlik are
in the Lead. Emerging
companies in the Niche
quadrant.
• There is an increasing
growth toward data
visualisation