2 1.5 Demonstrates reflection on the choice of research methods and
approaches, including any relevant issues or obstacles.
3 2.1 Selects credible sources of data
4 2.10 Recommends solutions that could be applied in practice
5 3.2 Expresses arguments coherently through writing
6 3.4 Displays good structure, formatting, style and presentation of writing
7 3.5 Cites sources of information and data using consistent and a recognised
referencing style
Assessment instructions for students (as per QMPlus ‘Assessment Information’ tab)
Client Background
The client, AIQ Limited, is a UK-based fully online retailer of gift products. Their strategic priorities for 2020-
2025 are Innovation (i.e. develop innovative products or business models/markets) and Internationalisation
(i.e. increase non-UK sales, in countries that they currently sell to and/or in new international markets) along
with ensuring the growth of the business (i.e. adding new revenue streams, business models). However, their
mid-term assessment in summer 2023 revealed that they are not on course to achieve these priorities
satisfactorily by 2025.
Therefore, you have been commissioned as a Management Consultant specialising in AI for Business to
analyse the situation and suggest a new course of action for the company to achieve its strategic goals. You
have been provided access to some sales data as part of this brief. You are expected to carry out further
research as necessary.
Data Description
The dataset you have been provided (SPSS file) contains sales data including the following variables: Quantity
(number of products sold), InvoiceDateTime (when the sale was made), Date (date of the sale converted into
an integer for modelling purposes), Unit Price (the price of the product per unit), Country (which country the
customer is from), Product (product type categorisation), country_select (UK vs. Non-UK customer), Profitability
(UK customers segmented according to profitability - incomplete), and training (variable for allocating the
training vs. test data).
NOTE:
It is recommended that the analyses required as part of this assignment are performed in SPSS.
DELIVERABLES – WHAT YOU NEED TO DO
You are required to produce a written report, which is presented in a professional style (as opposed to a
theoretical essay) with graphs/tables and references where relevant (these can include industry sources as well
as academic). The report should address the following:
1. Part A: Predict the profitability of international sales.
The Profitability variable provides a categorisation of UK sales according to their profitability
(low/medium/high). However, this task has not been completed for the international (non-UK) sales. The
client expects you to build a basic Artificial Neural Network (ANN) model to predict and understand the
profitability of international sales. Here are the relevant instructions:
· Initial Analysis - Perform ANN analysis. If in SPSS: Analyze > Neural Networks > Multilayer
Perceptron. Use the training variable as the partitioning variable to assign the training vs. test data,
and opt for the default settings (automatic architecture selection in SPSS).
In the report, describe which variables you selected, how you designated these in the model (i.e.
Dependent Variable, Factor, Covariate), and your evaluation of the model’s performance (e.g.
percentage of incorrect predictions). [5 Marks]
· Model Tuning - Make one change to the model and rerun the analysis. You could do this, for
example, by changing the number of hidden layers of the ANN model from one to two, or by
changing the activation function from Hyperbolic Tangent to Sigmoid – both of these changes can
be made in SPSS through the options in the ‘Architecture’ menu -> Custom Architecture.
In the report, describe the tuning task you performed with a brief rationale, and your evaluation of
the tuned model’s performance. Compare the performances of the tuned model to the initial model
(i.e. consider the pros and cons of each model) and state which model is better. [10 Marks]
Having selected the best model, run that model again, but this time save the predicted values for the
dependent variable. In SPSS, you can do this by ticking the “Save predicted value or category for
each dependent variable” box in the Save menu (see screenshot below).
Further, examine the relative importance of predictors. You can do this in SPSS via the Output
menu -> tick the box for “Independent Variable Importance Analysis” (see screenshot below).
· Compare the profitability of UK sales against non-UK sales – you may do this by cross-tabulating
the predicted profitability values with country_select variable (Analyze > Descriptive Statistics >
Crosstabs, and insert the Predicted Value for Profitability variable in Row(s) box and country_select
in Column(s) box) You can also ask for percentages by going into the “Cells” menu and ticking the
box for Column (see screenshot below); feel free to select the percentages for Row(s) as well. For
additional details, you can also include the Country variable in the Column(s) box.
In the report, first discuss the importance of the predictors (independent variables) for profitability in
general (UK and non-UK). Then, discuss the profitability of international sales vs. UK sales in as
much detail as possible. For example, you should discuss to what extent there is evidence for
pursuing internationalisation as one of the strategic priorities, and which countries may be attractive
markets based on the profitability analysis. [15 Marks]
2. Part B: Develop a segment-based internationalisation strategy.
The client is interested in understanding the different segments of customers they currently have, with a
view to using this knowledge for improved future targeting (and growth). The client expects you to conduct a
cluster analysis using the IBM SPSS TwoStep algorithm to identify and understand current customer
segments. The segmentation criteria should include the following variables: Date (i.e. recency of the sale),
Quantity (i.e. frequency of sale), Unit Price (i.e. monetary value), and country_select (i.e., whether it is a UK
or non-UK sale). Here are the relevant instructions:
· Initial Analysis – If using SPSS, perform a TwoStep Cluster analysis: Analyze > Classify > TwoStep
Cluster. Appropriately select the categorical and continuous variables among the segmentation
criteria (variables) mentioned above, and populate the “Categorical Variables” and “Continuous
Variables” boxes. Then, click on the Output tab and ensure that the two boxes at the top for “Pivot
Tables” and “Charts and Tables in Model Viewer” are both ticked. No other options need to be
changed/selected for the initial analysis.
In the report, discuss the initial cluster solution resulting from the above analysis. This should
include (as a minimum), an evaluation of the cluster solution returned (i.e. how well does the model
perform?), and the number, size, and characteristics of the clusters/segments (describe them
according to the segmentation criteria specified). [10 marks]
· Model Tuning - Make one change to the model and rerun the analysis. You could do this, for
example, in SPSS by changing the “Clustering Criterion” in the main window from BIC to AIC, or by
specifying a fixed number of clusters rather than selecting the “Determine Automatically” option (see
screenshot below). Then, compare the output from the tuned model to the initial model.
In the report, discuss the change you made to the initial model, offering a brief rationale for it. Then,
discuss the performance of the tuned model in comparison to the initial model – this will include
comparisons of the number, size, and characteristics of the segment solutions, as well as a
performance metric (i.e. Silhouette score in SPSS TwoStep clustering). Conclude by stating which
model is better based on your evaluation. [10 Marks]
Having selected the best model, run that model again, but this time save the predicted cluster
membership for each case. If using SPSS, you can do this by ticking the “Create cluster
membership variable” box in the Output menu (see screenshot below).
· Recommend an internationalisation strategy based on your analysis - the goal is to increase
profitability (sales revenue minus costs). To do this, examine the output from your best model again
and look at how the UK vs. non-UK sales are represented across your segments – this will tell you
which segments may be attractive to focus on if the goal is internationalisation. You may also get a
more in-depth view of countries by cross-tabulating the cluster membership variable (in SPSS, it will
start with TSC) with the Country variable (if using SPSS: Analyze > Descriptive Statistics >
Crosstabs, and insert the cluster membership variable in the Columns(s) box and Country in the
Row(s) box).
For details about which products may be appropriate for the segment(s) you target for
internationalisation, you can also include the Product variable in the Row(s) box in the cross-
tabulation menu in SPSS. You can ask for percentages by going into the “Cells” menu and ticking
the box for Column and Row(s) (same as in Part A).
In the report, first discuss the most attractive segment(s) for internationalisation. You can then
discuss specific countries (maximum 3) that are suitable for specific targeting within the attractive
segment you have chosen – when doing this, please consider the geographic proximity of the
country to UK and any other relevant factor, which could influence set-up and delivery costs for the
client. You may also incorporate any insights gained from your analysis of profitability in
international markets from Part A into your discussion and recommendations here. Following this,
you can discuss which types of products may be suitable, based on your analysis, for each specific
country within the segment that you are targeting. [15 Marks]
3. Part C: Discuss the potential for innovation based on emergent technologies.
As mentioned earlier, the client also considers innovation a priority alongside growth. So you have been
instructed to examine the potential for leveraging emergent technologies – specifically, the metaverse
(including NFTs, blockchain, cryptocurrency, and game engines) and service robots (including humanoid
robots, avatars, chatbots, and voice assistants) – for growing the client’s business through introduction of a
new business model or revenue stream. Here are the requirements:
· Conduct further research on the metaverse and service robots through academic sources, market
research databases (Mintel/WARC etc.), industry magazines (e.g. WIRED, The Verge), and reputed
media outlets (e.g. Financial Times, The Economist). Please cite your information sources
appropriately.
In the report, provide an introduction and a critical evaluation of these two technologies for the client,
highlighting the latest developments, and the positive and negative aspects of the technologies in
general. [15 Marks]
· Next, by incorporating relevant insights from Parts A & B and your knowledge of the client’s
business, discuss how the client may take advantage of the chosen technology. You could, for
example, consider an entirely new business model that can be pursued, any current products that
can be marketed/sold, or new products that can be developed utilising this technology. Also discuss
any disadvantages of the chosen technology for the client’s business. [15 Marks]
4. Overall presentation of the report – professional layout and report style appropriate for
business/executive readers, writing is clear and to the point, logical/coherent arguments to support points
and recommendations, charts/figures and tables (where applicable) to help readers understand key points
etc. [5 marks]
Submission Information
Please observe the following style guide. Unless otherwise specified
• All work must be typed and submitted in MS Word or Adobe PDF format
• Font size should be 12 point (unless otherwise specified)
• Font style should be Arial
• Lines should be double-spaced
• Leave margins for comment Insert page numbers
• Use a header containing your student ID number, the module code to which your work applies, and
the date. And Please:
• Always spell-check and proofread your work before handing it in (once you have submitted your
work you will not be permitted to retrieve it)
• Keep your own electronic back-up copy of your work and if possible, save on two devices
• Submit your work on time
• Avoid plagiarism
Guidelines and Late-Work Policy
1. Coursework submitted late (and there are no extenuating circumstances) will incur a late penalty. Five per
2. cent of the total marks available shall be deducted for every period of 24 hours, or part thereof, that an
assignment is overdue there shall be a deduction of five per cent of the total marks available (i.e. five marks
for an assessment marked out of 100). After seven calendar days (168 hours or more late) the mark shall
be reduced to zero, and recorded as 0FL (zero, fail, late).
3. Each module has word limits for coursework assignments; however, the decision about whether to impose
a penalty mark for exceeding the word limit is made by each module organiser. You must check the module
handbook and the assignment briefing documents to see whether the particular module organiser has
adopted a penalty system. It is your responsibility to read the handbook and assignment briefing carefully. If
no penalty is specified then the module organiser will take into account the word length under the standard
marking conventions. For example, if you have exceeded the word limit then it might be that you have not
been sufficiently succinct or focused in your assignment and therefore might be penalised for these
weaknesses. Please note that word limits do NOT include references or appendices. However if excessive
material is included on appendices then this too will be judged accordingly and you may be awarded a
lower mark.
4. You should ensure that your submission is in either Microsoft Word or PDF format.
5. Failure to submit in either one of these formats will result in a mark of 0 being awarded for the particular
assessment. It is therefore your responsibility to ensure that the file format is correct and it can be opened
by the receiving party.
6. You should ensure that the correct piece of assignment is uploaded as the document downloaded on the
due date by the module organiser will be marked regardless of content. You will not have another
opportunity to submit the work again if you mistakenly uploaded the wrong document.
7. ALLOW YOURSELF PLENTY OF TIME TO SUBMIT YOUR COURSEWORK. DO NOT LEAVE IT UNTIL
THE LAST MINUTE
8. Computer problems, such as computer viruses, failure to make a back-up copy or temporary internet
access problems, will NOT be viewed as a valid reason for late submission.
9. Check that your assignment submission has been successful, and print a copy of the confirmation screen.
10. If you submit your assignment after the deadline, you will still be able to submit your coursework via QMplus
however you will be penalised for late submission, the only exception to this is if you have an approved
extension due to extenuating circumstances.
Submission Deadline
Date 21 Dec 2023
Time 3pm
Help and Support
· Module Organiser
· Disability and Dyslexia Service (DDS)
· Quantitative Skills Tutor
· Academic Writing Skills Tutor
Marking Rubric
49% or less 50% – 59% 60% – 69% 70% +
Part A – C
(see
assessment
instructions
for marks
breakdown)
Poor understanding of
requirements. Submission does
not meet with the minimum
standard of work expected. This
could be in terms of not carrying
out the required analyses and/or
describing the necessary steps.
Discussion lacks insights and
logic. The contents do not
adequately reflect student’s own
analyses, arguments, and
recommendations/conclusions.
Little or no research input (where
relevant) to highlight wider
reading and understanding, and
to lend credibility to
recommendations/conclusions.
Basic understanding of
requirements has been achieved.
Submission meets the minimum
standard of work expected. This
could be in terms of carrying out
the required analyses and/or
describing the necessary steps,
with a few lapses. Discussion
requires greater insights and
logic. The contents reflect
student’s own analyses,
arguments, and
recommendations/conclusions to
a basic extent. Basic level of
research input (where relevant)
is evident.
Good understanding of
requirements. Submission
reflects a good standard of
work in terms of carrying out
the required analyses and
describing the necessary
steps. Discussion shows good
insights and is logical/justified,
although the arguments may
need to connect better with the
results from the analyses. The
contents reflect student’s own
analyses, arguments, and
recommendations/conclusions.
Good level of research input
(where relevant) is evident.
Excellent understanding of
requirements. Submission goes
beyond the standard of work
expected in terms of carrying out
the required analyses and
describing the necessary steps,
and drawing conclusions from
these. Discussion shows excellent
insights and is not only
logical/justified, but also integrates
insights from multiple sources. In-
depth analyses or insights have
been carried out or developed. The
contents reflect original analyses
and arguments, or
recommendations and conclusions.
Excellent level of research input
(where relevant) is evident.
Overall
structure
and
presentation
Very poor structure, which
makes the content incoherent
and/or incomprehensible in key
areas. The style of writing is very
abstract and theoretical and not
at all relevant to the practical
scenario(s) described in the
brief. No tables, graphs or
figures where relevant.
The structure is only marginally
professional, which makes the
content readable to a basic
extent. The style of writing is
somewhat abstract and
theoretical, but in some key
areas relevant to the practical
scenario(s) described in the brief.
Basic tables/graphs/figures
included, and/or without much
integration with the discussion.
The structure is professional,
and the content is readable to
a good extent. The style of
writing is not abstract and
theoretical, and practical with
good relevance to the case
scenario(s) described in the
brief. Good inclusion of
tables/graphs/figures in
connection to the discussion.
The structure is very professional,
the content is very clear and
presented in an excellent manner.
The style of writing is outstanding
in that it is relevant and to-the-
point, but also shows a lot of
critical thought and analytical
strength. Outstanding use of
tables/graphs/figures in connection
to the discussion, which not only
enhances the presentation, but
adds to the strength of the reports
recommendations/conclusions.
