data留学生程序讲解、辅导Python，C++，Java编程 讲解数据库SQL|辅导留学生 Statistics统计、回归、迭代
- 首页 >> Matlab编程 CRANFIELD UNIVERSITY
CRANFIELD SCHOOL OF MANAGEMENT
MSC LOGISTICS AND SUPPLY CHAIN MANAGEMENT
MSC PROCUREMENT AND SUPPLY CHAIN MANAGEMENT
BIG DATA ANALYTICS
ASSIGNMENT
Date Set: 29 March 2021
Date Due: 19 April 2021
2 of 7
Introduction
In this Big Data Analytics Assignment, you will be assessed in two areas: theory and practice.
In the theory area, we expect you to critique recent publications in the big data analytics
domain. In the practice area, we present you with datasets on which we expect you to perform
appropriate analysis and draw managerial conclusions. Each of these areas will comprise 45%
of your marks. As is the case in many other assignments, 10% of the marks are attributable
to style and presentation.
The word limit for this assignment is 1,500. It is an upper limit, not a target. Please report the
number of words and do not exceed this limit (this includes references). Although theory
and practice questions are equally weighted, we anticipate you will use more words in the
theory part, roughly 2/3 of your upper limit.
Please use the discussion board for any questions you might have about this assignment. We
will answer all questions that are asked on or before 15 April 2021 -12 pm to minimise the lastminute
stress and encourage timely attention to the assignment.
It has been an absolute pleasure to teach you big data analytics. We hope you enjoy this
assignment and use the techniques in the future.
Dr Abhijeet Ghadge, Prof Emel Aktas
March 2021, Cranfield University, UK.
Disclaimer: Although the problems presented in this assignment are informed by real
events, the names, characters, businesses, places, events, locales, and incidents are the
products of the authors’ imagination. Any resemblance to actual persons, actual businesses,
or actual events is coincidental.
3 of 7
Q1 Theory [45 marks]
Identify three recent academic papers- two on predictive analytics and one on prescriptive
analytics within logistics and supply chain problem context.
Critically discuss the application of predictive and prescriptive analytical techniques
for improving supply chain performance.
Using your favourite research database (e.g. Scopus), search and select three papers that
explain the application of different predictive and prescriptive analytical techniques to solve
logistics/supply chain problem. Please do not use a literature review paper in your selection.
We are looking for applied research papers. Don’t forget to include selected three papers in
the list of references. Please highlight them separately (in bold) to other references that you
may use.
Q2 Practice [45 marks]
For the practical part of the assignment, we have prepared datasets for you to replicate the
analyses we have done in the module to a larger extent. For this purpose, we have an affinity
analysis exercise, where we have done some of the preprocessing on the company’s data to
assist you. Affinity analysis helps us determine which products are likely to be ordered
together. It relies on the number of occurrences of instances and presents a confidence score
for the likelihood of two products being bought together to inform warehouse layout decisions
(e.g. using the output of your analysis, the manager may decide to put the products bought
together in closeby locations to reduce the picking time). The confidence score is the number
of instances Product 1 and Product 2 were bought together over total instances Product 1 was
bought. Product 1 in this case is the first product mentioned in the rule.
In the “affinity_data_and_product_names.zip” file, you will find two text files:
1. affinity_data.txt
2. affinity_productnames.txt
“affinity_data.txt” has the orders placed with a company over a four-month period in 2019.
Each row indicates an order and each column is the products held in stock by the company.
The data is made of 0s and 1s where 1 indicates that the product was in the given order. This
data file comprises 67844 orders of 21447 products, so it will take a while to load to memory
depending on your computer.
4 of 7
“affinity_productnames.txt” has the names of the products that you will need to use when
reporting your findings.
Please report the descriptive statistics for the number of products in an order (min, Q1,
median, Q3, max, mean, standard deviation). Please note that we are asking for the
descriptive statistics of one variable: the number of products in an order, which you will have
to calculate before you produce the descriptive statistics.
Please perform an affinity analysis exercise on this data to draw the top five rules with the
highest support for the occurrence of two products together. In your response, we expect
you to present the support and the confidence in the rule with the corresponding product
names.
Please add your script as an appendix with appropriate comments.
Style and Presentation [10 marks]
You will receive marks for the style and presentation of your assignment. Please pay
attention to
1. Writing grammatically correctly and concisely.
2. Providing captions for your tables and figures and citing them in the text.
3. Using an appropriate level of accuracy (no need for 5+ figures after the decimal
point. We recommend 3).
4. Presenting your assignment in a report structure, so we can map your answers to the
questions we have asked.
5. Citing the references you used in preparing your answers.
Marking Criteria
Marks will be awarded for the level of understanding demonstrated in the concepts and accuracy of your answers.
ASSESSMENT
CRITERIA
Very poor (0-
39%)
Poor (40-49%) Satisfactory
(50-59%)
Good(60-69%) Very good
(70-79%)
Excellent
(80-100%)
Theory [45]
Publication time
of papers [5]
Papers
missing.
Papers
selected were
published more
than a decade
ago.
Papers selected
are published
within the last
decade.
Papers
selected are
published within
the last five years.
Papers
selected are
published within
the last three
years.
Papers
selected are
recent (2020-
2021).
Relevance of
papers [10]
Papers
missing.
Papers are not
relevant to
logistics & supply
chain
management.
Papers have
questionable
relevance to for
logistics & supply
chain
management.
Papers are
somewhat
relevant to
logistics & supply
chain
management.
Papers are
mostly relevant to
logistics & supply
chain
management.
Papers are
relevant to
logistics & supply
chain
management.
Comparison
[20]
Papers not
compared.
Comparison
arguments are not
valid at times.
Comparison
criteria identified
have questionable
appropriateness to
the task at hand
and evaluation of
the papers is
questionable.
Somewhat
appropriate
comparison
criteria are
identified and
applied somewhat
competently.
Mostly
appropriate
comparison
criteria are
identified and
applied mostly
competently.
Appropriate
comparison
criteria are
identified and
applied
competently.
Reflection [10] There are no
reflections.
Reflections are
not specific to the
area identified.
Reflections are
general and basic.
Reflections
lack sufficient
detail at times.
Reflections are
detailed.
Reflections are
detailed and
referenced.
6 of 7
ASSESSMENT
CRITERIA
Very poor (0-
39%)
Poor (40-49%) Satisfactory
(50-59%)
Good(60-69%) Very good
(70-79%)
Excellent
(80-100%)
Practice [45]
Descriptive
Statistics [10]
Descriptive
Statistics missing.
Descriptive
statistics
produced but has
some errors.
Descriptive
statistics is
produced and
presented without
any commentary.
Descriptive
statistics is
produced and
presented with
some
commentary.
Descriptive
statistics is
produced and
presented clearly
with key
conclusions.
Descriptive
statistics is
produced and
presented clearly
with all applicable
conclusions.
Model Build
and Test [25]
No model built. Model build
steps and choices
made by the
author not
explained.
Main steps to
build the model
are presented
without any
explanation.
The main
steps to build the
model are
explained.
The steps to
build the model
explained without
any justification.
The steps to
build the model
explained well and
the model choice
justified.
Insights [10] No
recommendations
produced.
The link
between
recommendations
and the results is
missing.
Few
recommendations
are produced for
the company
without
justification.
Few
recommendations
are produced for
the company and
justified by
somewhat
relevant
examples.
Several
meaningful
recommendations
produced for the
company and
justified by
relevant
examples.
Data-driven,
meaningful
recommendations
are produced for
the company and
justified by
references and
relevant
examples.
7 of 7
ASSESSMENT
CRITERIA
Very poor (0-
39%)
Poor (40-49%) Satisfactory
(50-59%)
Good(60-69%) Very good
(70-79%)
Excellent
(80-100%)
Style and
Presentation
[10]
Coherence and
conciseness of
writing. Good
grammar, no
spelling errors,
and use of
appropriate
vocabulary.
Language far
from fluent,
meaning unclear,
grammar and/or
spelling poor.
Language far
from fluent but
understandable,
grammar and/or
spelling poor.
Language
understandable,
meaning apparent
but not explicit,
grammar and/or
spelling poor.
Language
mainly fluent,
minor spelling
and/or grammar
and/or
punctuation
errors.
Language
fluent thoughts
and ideas clearly
expressed.
Exceptionally
fluent structure,
and clarity of
expression.
Relevant and
accurate
referencing
Incoherent
and/or absent
referencing.
Inconsistent,
incoherent
referencing.
Inconsistent,
referencing with
some errors.
Referencing,
relevant but with
several errors.
Referencing,
relevant with few
errors.
Referencing
clear, relevant and
consistent.
Virtually errorfree.
Effective and
well-presented
figures and
tables
Table and
figure captions
are missing.
Tables and
Figures not cited
in the text.
Table and
figure captions
missing or
inconsistent.
Tables and
Figures cited
wrongly in the
text.
Table and
figure captions
with minimal
information.
Tables and
Figures are not
always cited in the
text and
sometimes spilling
over the margins.
Table and
figure captions
are sometimes
meaningful.
Tables and
Figures are
sometimes cited
in the text.
Table and
figure captions
are meaningful.
Tables and
Figures are
consistently cited
in the text.
Table and
figure captions are
meaningful.
Tables and
Figures cited in
the text. No
spillage on the
page margins.
CRANFIELD SCHOOL OF MANAGEMENT
MSC LOGISTICS AND SUPPLY CHAIN MANAGEMENT
MSC PROCUREMENT AND SUPPLY CHAIN MANAGEMENT
BIG DATA ANALYTICS
ASSIGNMENT
Date Set: 29 March 2021
Date Due: 19 April 2021
2 of 7
Introduction
In this Big Data Analytics Assignment, you will be assessed in two areas: theory and practice.
In the theory area, we expect you to critique recent publications in the big data analytics
domain. In the practice area, we present you with datasets on which we expect you to perform
appropriate analysis and draw managerial conclusions. Each of these areas will comprise 45%
of your marks. As is the case in many other assignments, 10% of the marks are attributable
to style and presentation.
The word limit for this assignment is 1,500. It is an upper limit, not a target. Please report the
number of words and do not exceed this limit (this includes references). Although theory
and practice questions are equally weighted, we anticipate you will use more words in the
theory part, roughly 2/3 of your upper limit.
Please use the discussion board for any questions you might have about this assignment. We
will answer all questions that are asked on or before 15 April 2021 -12 pm to minimise the lastminute
stress and encourage timely attention to the assignment.
It has been an absolute pleasure to teach you big data analytics. We hope you enjoy this
assignment and use the techniques in the future.
Dr Abhijeet Ghadge, Prof Emel Aktas
March 2021, Cranfield University, UK.
Disclaimer: Although the problems presented in this assignment are informed by real
events, the names, characters, businesses, places, events, locales, and incidents are the
products of the authors’ imagination. Any resemblance to actual persons, actual businesses,
or actual events is coincidental.
3 of 7
Q1 Theory [45 marks]
Identify three recent academic papers- two on predictive analytics and one on prescriptive
analytics within logistics and supply chain problem context.
Critically discuss the application of predictive and prescriptive analytical techniques
for improving supply chain performance.
Using your favourite research database (e.g. Scopus), search and select three papers that
explain the application of different predictive and prescriptive analytical techniques to solve
logistics/supply chain problem. Please do not use a literature review paper in your selection.
We are looking for applied research papers. Don’t forget to include selected three papers in
the list of references. Please highlight them separately (in bold) to other references that you
may use.
Q2 Practice [45 marks]
For the practical part of the assignment, we have prepared datasets for you to replicate the
analyses we have done in the module to a larger extent. For this purpose, we have an affinity
analysis exercise, where we have done some of the preprocessing on the company’s data to
assist you. Affinity analysis helps us determine which products are likely to be ordered
together. It relies on the number of occurrences of instances and presents a confidence score
for the likelihood of two products being bought together to inform warehouse layout decisions
(e.g. using the output of your analysis, the manager may decide to put the products bought
together in closeby locations to reduce the picking time). The confidence score is the number
of instances Product 1 and Product 2 were bought together over total instances Product 1 was
bought. Product 1 in this case is the first product mentioned in the rule.
In the “affinity_data_and_product_names.zip” file, you will find two text files:
1. affinity_data.txt
2. affinity_productnames.txt
“affinity_data.txt” has the orders placed with a company over a four-month period in 2019.
Each row indicates an order and each column is the products held in stock by the company.
The data is made of 0s and 1s where 1 indicates that the product was in the given order. This
data file comprises 67844 orders of 21447 products, so it will take a while to load to memory
depending on your computer.
4 of 7
“affinity_productnames.txt” has the names of the products that you will need to use when
reporting your findings.
Please report the descriptive statistics for the number of products in an order (min, Q1,
median, Q3, max, mean, standard deviation). Please note that we are asking for the
descriptive statistics of one variable: the number of products in an order, which you will have
to calculate before you produce the descriptive statistics.
Please perform an affinity analysis exercise on this data to draw the top five rules with the
highest support for the occurrence of two products together. In your response, we expect
you to present the support and the confidence in the rule with the corresponding product
names.
Please add your script as an appendix with appropriate comments.
Style and Presentation [10 marks]
You will receive marks for the style and presentation of your assignment. Please pay
attention to
1. Writing grammatically correctly and concisely.
2. Providing captions for your tables and figures and citing them in the text.
3. Using an appropriate level of accuracy (no need for 5+ figures after the decimal
point. We recommend 3).
4. Presenting your assignment in a report structure, so we can map your answers to the
questions we have asked.
5. Citing the references you used in preparing your answers.
Marking Criteria
Marks will be awarded for the level of understanding demonstrated in the concepts and accuracy of your answers.
ASSESSMENT
CRITERIA
Very poor (0-
39%)
Poor (40-49%) Satisfactory
(50-59%)
Good(60-69%) Very good
(70-79%)
Excellent
(80-100%)
Theory [45]
Publication time
of papers [5]
Papers
missing.
Papers
selected were
published more
than a decade
ago.
Papers selected
are published
within the last
decade.
Papers
selected are
published within
the last five years.
Papers
selected are
published within
the last three
years.
Papers
selected are
recent (2020-
2021).
Relevance of
papers [10]
Papers
missing.
Papers are not
relevant to
logistics & supply
chain
management.
Papers have
questionable
relevance to for
logistics & supply
chain
management.
Papers are
somewhat
relevant to
logistics & supply
chain
management.
Papers are
mostly relevant to
logistics & supply
chain
management.
Papers are
relevant to
logistics & supply
chain
management.
Comparison
[20]
Papers not
compared.
Comparison
arguments are not
valid at times.
Comparison
criteria identified
have questionable
appropriateness to
the task at hand
and evaluation of
the papers is
questionable.
Somewhat
appropriate
comparison
criteria are
identified and
applied somewhat
competently.
Mostly
appropriate
comparison
criteria are
identified and
applied mostly
competently.
Appropriate
comparison
criteria are
identified and
applied
competently.
Reflection [10] There are no
reflections.
Reflections are
not specific to the
area identified.
Reflections are
general and basic.
Reflections
lack sufficient
detail at times.
Reflections are
detailed.
Reflections are
detailed and
referenced.
6 of 7
ASSESSMENT
CRITERIA
Very poor (0-
39%)
Poor (40-49%) Satisfactory
(50-59%)
Good(60-69%) Very good
(70-79%)
Excellent
(80-100%)
Practice [45]
Descriptive
Statistics [10]
Descriptive
Statistics missing.
Descriptive
statistics
produced but has
some errors.
Descriptive
statistics is
produced and
presented without
any commentary.
Descriptive
statistics is
produced and
presented with
some
commentary.
Descriptive
statistics is
produced and
presented clearly
with key
conclusions.
Descriptive
statistics is
produced and
presented clearly
with all applicable
conclusions.
Model Build
and Test [25]
No model built. Model build
steps and choices
made by the
author not
explained.
Main steps to
build the model
are presented
without any
explanation.
The main
steps to build the
model are
explained.
The steps to
build the model
explained without
any justification.
The steps to
build the model
explained well and
the model choice
justified.
Insights [10] No
recommendations
produced.
The link
between
recommendations
and the results is
missing.
Few
recommendations
are produced for
the company
without
justification.
Few
recommendations
are produced for
the company and
justified by
somewhat
relevant
examples.
Several
meaningful
recommendations
produced for the
company and
justified by
relevant
examples.
Data-driven,
meaningful
recommendations
are produced for
the company and
justified by
references and
relevant
examples.
7 of 7
ASSESSMENT
CRITERIA
Very poor (0-
39%)
Poor (40-49%) Satisfactory
(50-59%)
Good(60-69%) Very good
(70-79%)
Excellent
(80-100%)
Style and
Presentation
[10]
Coherence and
conciseness of
writing. Good
grammar, no
spelling errors,
and use of
appropriate
vocabulary.
Language far
from fluent,
meaning unclear,
grammar and/or
spelling poor.
Language far
from fluent but
understandable,
grammar and/or
spelling poor.
Language
understandable,
meaning apparent
but not explicit,
grammar and/or
spelling poor.
Language
mainly fluent,
minor spelling
and/or grammar
and/or
punctuation
errors.
Language
fluent thoughts
and ideas clearly
expressed.
Exceptionally
fluent structure,
and clarity of
expression.
Relevant and
accurate
referencing
Incoherent
and/or absent
referencing.
Inconsistent,
incoherent
referencing.
Inconsistent,
referencing with
some errors.
Referencing,
relevant but with
several errors.
Referencing,
relevant with few
errors.
Referencing
clear, relevant and
consistent.
Virtually errorfree.
Effective and
well-presented
figures and
tables
Table and
figure captions
are missing.
Tables and
Figures not cited
in the text.
Table and
figure captions
missing or
inconsistent.
Tables and
Figures cited
wrongly in the
text.
Table and
figure captions
with minimal
information.
Tables and
Figures are not
always cited in the
text and
sometimes spilling
over the margins.
Table and
figure captions
are sometimes
meaningful.
Tables and
Figures are
sometimes cited
in the text.
Table and
figure captions
are meaningful.
Tables and
Figures are
consistently cited
in the text.
Table and
figure captions are
meaningful.
Tables and
Figures cited in
the text. No
spillage on the
page margins.