1

BISM2204 METHODS OF BUSINESS ANALYTICS

Project Report – Briefing Notes (Updated with rubric, 13/05/2021)

Background

The course BISM2204 Methods of Business Analytics has three assessment items: a project plan, a
project report, and a final examination (a “take home” exam). These notes outline my expectations
for the project report. Keep in mind that the project report is intended as an extension of the
project plan. The plan proposed a possible direction for your project. The project report restates
key elements of the plan, documents the methods and results of your project, and highlights the
implications for the client (for example, Spotify). Note the project report should be prepared and
submitted in PowerPoint format (whereas the project plan was in the form of a Word document).
Furthermore, you can if you wish record yourself presenting your PowerPoint slide deck and submit
the recording.

The overall aim of the report should be to provide “proof of concept” for your ideas; that is, initial
evidence to support your claim that something like the approach you are taking is capable of
generating “business value” for the client. The report should be comprehensive – sketching out all
aspects of the project from beginning to end. Draw on your proposal where it is appropriate to do
so – you can use the text you wrote for the proposal (“self-plagiarism” in the project is OK, the
project is an extension of the plan). Make some revisions if you think you can improve upon the
proposal. For our purposes, the proposal is not a binding document. That is to say, you are very
welcome to revise your proposal if you think revision is needed to it. (Perhaps you should signal to
the reader of your project report how your project differs from the proposal and why, if it does differ
from it in meaningful ways.)

Furthermore, you will need to find the right balance between the effort you put into the technical
aspects of your project and in communicating the value of your project – with the overall goal of
having impact on the client business. This is perhaps the key decision you will have to make in
coming weeks. One way to reconcile the possible tension between the demands of your project and
the reporting requirements is to style your project as a pilot project. Let me elaborate. I do not
expect your report to provide a definitive answer to the business problem you are address, but I do
expect you to generate an indicative solution to the problem (for example, generating a regression
model that addresses the problem and providing an interpretation of that model). My expectation is
that the report will provide indicative answers, show what is possible, and provide you with the
experience to say with greater confidence what type of project would more definitively address the
problem. What is the next analytics project the client should consider?

Key Sections

The project report will likely have the following sections.

1. Background
2. Business problem
3. Proposed solution/method of analysis
4. Analysis plan
5. Results and interpretation
6. Strategy/recommendations (and business case)
7. Conclusion
2

You might be able to think of a different structure – this is a guide only, but one that should be
useful. Per the project plan, the background section introduces the project, placing emphasis on the
broad context and highlighting the specific domain of interest (in this case, the importance of
business analytics to the music industry). The general expectation is some key business process
and/or management decision will be improved through the use of analytics reported in your project
report.

The next section of the report should restate the business problem you are attempting to address.
What is the problem you are trying to solve? A starting point might be to specify an outcome the
target business/client is trying to achieve (for example, “song hotness”). Addressing the following
questions may help. (1) What is the specific outcome the business is trying to influence or
understand, or both? (2) How is it manifest or measured? (3) What level of that outcome variable
has the business achieved to date (or what is the average level of song hotness), and what is the
desired level of the outcome variable? (4) What are the likely factors or other variables that are
potentially related to the outcome of interest, and how are they measured?

The section on the proposed solution or “line of attack” should focus on the method of analysis – a
particular method of business analytics suitable for the problem you have outlined/specified (for
example, linear regression). Describe the method in some detail. Highlight the key steps and/or
issues in its implementation. For example, an application of predictive analytics might have linear
regression as it core modelling framework. This section should also outline the data requirements
needed to solve the business problem. In summary, this section should be specific about the
proposed method of analysis and the data to be used. The section should clearly identify and
describe the key output and feature variables, including writing the model in formal fashion
(perhaps supported by a path diagram).

The analysis plan is intended as a step-by-step guide to implementing the proposed approach. For
example, a regression analysis might involve several key steps, including a consideration of the
appropriateness of the data for the planned application, the specification of the outcome and input
variables, and some assessment of the how the basic assumptions of regression might be satisfied.
This section should now be much easy to write than it was for the proposal – having now had the
experience of analysing the data and developing the interpretations. Perhaps this section leads off
with approaches to visualising the data (univariate and bivariate) and the descriptive statistics that
will be reported, before outlining your approach to predictive modelling (including a report of
testing assumptions, etc.).

The results and interpretation may be in three parts. Firstly, you might provide some summary
information about the dataset you are working with. How many observations are you working with?
How many variables are you working with? Second, you might provide a more specific statistical
summary of the data. Reporting summary statistics is important, for example, what are the means
and standard deviations of the (continuous) variables? Are the variables normally distributed or
approximately normal? This is especially important for the outcome or dependent variable of a
linear regression model. Can you visual some of the key relationships by reporting scatterplots?
Third, you might report the results of any statistical analysis or modelling such as the results of a
regression model. (You may need to reformat some of the R output you generate. Any charts can
be included without any reformatting.)

Provide a written interpretation of each of the outputs you include in your report. Take the case of
reporting a regression model, for example. It is important to report (1) information about the
overall fit of the model to the data and (2) information about the importance of each of the input or
explanatory variables in the model. The adjusted R-squared provides a measure of overall fit of the
3

model to the data – higher values implying better fit. The F-statistic tests overall significance of the
model. The strength and significance of the regression coefficients provides insight into the
importance of each of the feature variables in the prediction of the output variable. In regression, t-
statistics are computed for each predictor variable.

Perhaps the key section of the report is the strategy and recommendations section. In effect, you
present the implications of your project in this section. Think about the value of your results from
the perspective of the client (for example, Spotify). What insights have you generated that might be
important for the client to know? Can you think of four or five key points? Given your results, are
there things the client should do more of or things the client should do less or of stop doing? Where
should the client start in actioning your results? What is the single most important thing the client
should do? What should the client do first, second, etc. As you start to address these questions, you
might find that your insights become the precursor for a set of recommendations. Also, think about
some of the potential costs associated with your recommendations. What might be more or less
feasible for the client?

Finally, I would like you to include a section on further research in your project reports. Think about
what should be done next – what is the next project, what does it look like? One way to think about
this question is to think about what you pilot project could have achieved if you had more time,
more data, and more resources. What would you have done differently if you had had more time
and resources? Another way to address the question of what further research should be done is to
focus on one or more very specific findings from your project. These might be unusual or
unexpected findings, or findings that may have great significance for the client but were only
addressed in part in your project. A good project finishes by outlining the next project a business
analysts might address!

Submission Guidelines

The report is worth 50 percent of your score in the course. In terms of length, I would expect your
PowerPoint doc to be in the range of 20-30 slides (maximum). You can start your PowerPoint doc
now – extract the key information from your proposal you wish to bring forward into the report, or
rewrite or write these early sections including the business problem, proposed solution, method of
analysis, data, analysis plan. Think about how best to present your results. Recall that visual and
statistical information might be reported – supported by short written descriptions of the key
results. Finally, consider the possibility of recording yourself presenting your presentation and
submitting the presentation file to me (for example, you could make and send me a Zoom
recording).

Check the electronic course profile for submission dates. Requests for extensions beyond this due
date should be made to me in written form via email. Please use the Turnitin link on the course
Blackboard site to submit your PowerPoint slide deck. I will consider the submission of your
PowerPoint file to the Turnitin link to be the official submission of your project report. Finally,
please email me the R script (the .R file) you create for your project. Ensure the script includes
everything you have used to produce your results.

• The .pptx file (the PowerPoint file)
• The .R file (the R script)

Submit the .pptx and .R file online using the submission link on BlackBoard.
A copy of the marking rubric is available on the next page.
4

Grade/Criterion Pass “4”
Functional achievement
Credit “5”
Proficient achievement
Distinction “6”
Advanced achievement
High Distinction “7”
Exceptional achievement
Revised Background
5%

Project is introduced with some attempt to motivate the project
Clear introduction of project, good motivation for project
Clear introduction of project, recognises broader context, excellent motivation for project
Clear and original introduction of
project, recognises broader context –makes nonobvious links, excellent motivation for project
Revised Business
Problem
5%
Offers an attempt at specifying the problem, identifies output and feature variables, key detail lacking in some respects
Offers a clear specification of the problem with some detail, identifies output and feature variables
Offers a clear and detailed specification of the problem – motivating the output and feature variables, brings a new perspective to the problem
Offers a clear and detailed specification of the problem – motivating the output and feature variables, brings an original
perspective to the problem
Revised Proposed
Solution/Method of
analysis
5%
Summarises the approach to the problem, missing some key details (core assumptions and/or data requirements)
Summarises the approach to solving the problem – identifies an appropriate method of analysis, some consideration of
assumptions/data requirements
Summarises a generally thoughtful solution to the problem – identifies a method of analysis with some explanation of assumptions and data requirements
Summarises a thoughtful approach to solving the problem – identifies and provides a rationale for the method of analysis including assumptions and data requirements
Revised Analysis Plan
5%
Attempt at outlining the analysis plan, often lacking in key details and/or description of nature/form of results
Generally clear description of analysis plan, some attention to tests of assumptions and nature/form of the results
Clear and often detailed description of the analysis plan, noting how assumptions will be tested and the general steps needed to follow to produce results
Clear and detailed description of the analysis plan, noting how assumptions will be tested, giving highly specific details for each step of the analysis, and demonstrates how the results will be interpreted.
Results and Interpretation
30%
Provides a summary of the dataset but is missing information on variable distributions. There are errors or omissions in the reporting of other key statistics and models.
Provides some summary of the dataset, distributions of the key variables and correctly interprets key statistics.
Particular attention is given to overall model fit and significant coefficients.
Provides a good summary of the dataset, distributions of the key variables and correctly interprets key statistics. Particular attention is given to overall model fit and significant coefficients. Extensions to the basic analysis might be attempted.
Provides a detailed summary of the dataset, distributions of the key variables and correctly interprets key statistics. Particular attention is given to overall model fit and significant coefficients. Extensions to the basic analysis are well executed and demonstrate above average skills in the use of various methods of business analytics.
5

Strategy and Recommendations
30%
Lists a few recommendations and suggests some further research.
Provides a set of guidelines to the client but some of these are based on conjecture rather than the data provided.
A future research project is mentioned.
Provides a clear set of guidelines to the client based on the results of the analysis. The recommendations are both tractable and realistically achievable and an outline for a future research project is provided.
Provides a clear set of guidelines to the client based on the results of the analysis. The recommendations are both tractable and realistically achievable. Unusual or unexpected findings are discussed and a detailed outline for a future research project are provided that directly builds upon the insights from this report.