Data Design- Part 2

This document discusses various aspects of data design, including business understanding, data collection and understanding, data integration, and inferential statistics. It provides insights into the importance of supply chain management, data collection methods, and statistical analysis techniques. The document also includes two datasets related to supply chain management in Aldi and discusses their relevance and limitations. Overall, it offers valuable information for anyone interested in data design and analysis.

Data Design- Part 2
1

Table of Contents
BUSINESS UNDERSTANDING...................................................................................................3
DATA COLLECTION AND UNDERSTANDING.......................................................................4
DATA INTEGRATION..................................................................................................................5
INFERENTIAL STATISTICS........................................................................................................6
DEPLOYMENT ETHICS AND CONCLUSION.........................................................................17
REFERENCES..............................................................................................................................19
Appendix........................................................................................................................................20
2

BUSINESS UNDERSTANDING
For every business it is important to manage its supply chain so that cost can be reduced.
The supply chain management is integral part of organisation. The overall production and
delivering of goods depend on SCM. However, if costs are not properly managed and controlled
it impact on business efficiency. (Dong, Ma and Xin, 2017)
Supply chain plays a vital role in managing, storing, stock as well as inventory. It is an
integral part of business where all activities are interrelated to each other. The track records of
finished products and raw material are kept to ensure they are delivered to vendors or suppliers at
right time. With help of supply chain, business is able to gain competitive advantage. Having a
better supply chain increases efficiency of business. If goods are delivered on time it helps in
generating customer value. Moreover, entire operating cost depend on supply chain. The main
objective is to identify strategies to reduce the cost of supply chain in Aldi. this is because it will
help in generating more profits and decreasing operational cost. It is identified that there are
various types of business objectives. They are economic, social global, operational, etc. These all
objectives are categorised on basis of its size and area. They are short, medium and long term
objectives. Thus, the above objective target on supply chain management and is a long term
objective. However, type of business objective is cost based. (Barday, 2018)
The consequences of this business objective for Aldi is that extra cost incurred in supply
chain will be minimised. In addition, the overall process of supply chain will be improved. This
means that suppliers and vendors records are maintained. Along with it, with help of strategies
delivery and arrival date of raw materials is tracked and recorded in effective way. besides that,
in future Aldi can gain value from supply chain. This will also result in enhancing efficiency and
eliminating deviations from the process. In addition to it, Aldi SCM process will become flexible
and quick. Hence, Aldi will be able to gain competitive advantage in retail sector in the future.
In order to collect data and information about supply chain management of Aldi and to get
answer of research question, there are certain requirements which is to be taken into
consideration. Also, data collection depends on type of question. It is important to analyse the
data requirement so that questions can be prepared. Alongside, as data is of various types the
main thing to be consider is validity, reliability, etc. besides that, in present study, a survey is
conducted to gather data of supply chain. It is because of as Aldi contains a lot of vendors that
are located in different regions. Moreover, the survey is suitable tool for data collection.
3

However, unit of analysis is large and suppliers need to be asked specific questions.
Furthermore, it is evaluated that implication of survey is all data related to schedule, supplier,
unit cost, etc. will be gathered easily. Also, survey will be easy to conduct and by analysing data
relevant information can be obtained. (Varley, Miglio and Hautier, 2017)
However, there are certain risk that can occur in data analysis. It can highly impact on
validity and outcomes of research. So, by doing risk assessment impact of risk can be minimised.
Thus, risk are as follows :-
Applicability- In this risk the data gathered through survey may not be applicable. The data
collected is irrelevant.
Availability of resources- here, resources required to collect data may not be available. It will
highly impact on authenticity of data. Also, ineffective utilization of resources may lead to rise in
cost of study.
Ethics – ethics risk may occur if data is not properly gathered. It means that without consent of
participants data is collected. Moreover, data is collected from third party, database, etc.
Time - it is a risk where there may be delay in research. Therefore, with increase in time, cost
will also increase.
There are various business rules that needs to be applied. The data must not be shared
with any third party. Also, data could only be used in developing practices and solving cost
reduction. The data collected must be relevant to business. Hence, these are rules that has to be
followed. (Hsu and Kuo, 2017)
DATA COLLECTION AND UNDERSTANDING
Dataset 1
The dataset is entirely related to supply chain of Aldi. In this many elements are included
like unit price, vendor, schedule date and time, etc. Moreover, it includes type of raw material,
supplier name, etc. the data is gathered from suppliers of Aldi. It is been gathered through survey
in which questions are asked to them. In data set country name, delivery date to third party, is
shown. This dataset applies to Aldi as it reflects on price, weight, freight cost, etc. of raw
materials. Therefore, by identifying cost and unit price it will be easy to apply strategies to
reduce cost. Along with it, it will be identified that how much variation each vendor has on cost
in same country. The tool that was used to collect data is survey. In that sample population taken
was 30 suppliers. While in collecting data, it was considered that no sample is discriminated on
4

basis of profit or sales. Moreover, it was ensured that supplier provide precise and relevant data
only.
Dataset 2
This dataset includes data of supplier, price, discount, customer feedback, etc. Through
that it is easy to find out identify out that how changing mode of shipment can result in bringing
variation in price. Besides that, data set provide detail of city, quantity, etc. in which products are
delivered to customers. The delivery and order date of product is mentioned as well. Thus, it will
be easy for organisation to calculate that how price of product can be reduced and how on basis
of customer feedback supplier can be selected (Kim, Schweickart and Pfister, 2016). However,
for data gathering survey tool was is selected. The sample population is 30 vendors. While in
collecting data, it was considered that no sample is discriminated on basis of profit or sales.
Moreover, no supplier was ignored on basis of city and its performance.
DATA INTEGRATION
It can be determined that the dataset collected is in tabular format. In that each column
represent a different variable. Moreover, each column the text used to describe is variable. Also,
data values is represented in key value pair format. In dataset no metadata records are included.
Datasets normally contain one or more data records from a single source representing the same
type of instance(s). However, the flexibility of a dataset can accommodate any other less-usual
use cases. Datasets may reside on the Web as well as be stored locally. Each dataset is uniquely
identified with standard metadata characterizations.
It can be identified that in dataset there are many variables which is missing. Due to it,
outcomes obtained from it is also affected. The variables missing are practices used by supplier,
distance covered, number of products delivered or sold, etc. Apart from it, other variables such
as total cost incurred, profit, variable cost, etc. therefore, in future research these variables can be
used and identified. It will provide in depth and detailed information related to how cost can be
reduced in supply chain. (Antons and Breidbach, 2018)
Exploratory analysis- it is a process of analyze data to identify main characteristics. It is a
statistical method to interpret data. With help of EDA it becomes easy to identify what data can
tell in future. Also, hypothesis testing is done in this. The approach is based on visualization to
obtain results of data.
5

INFERENTIAL STATISTICS
In order to interpret data and obtain relevant outcomes, it is essential to use data analysis
type. This is because it will help in finding whether results obtained are effective or not. Thus, in
present analysis t test, chi square, correlation and regression will be used. By using them it will
be easy to determine dependency of variables on one another. For using these tests, various
assumptions are made. Here, SPSS tool is used which will generate statistical data. Also, it will
help in identifying relationship between variables.
The experimental design is not used because it will not be useful in finding proper
outcomes. Also, cost can not be identified by doing experiment (Bimonte, Sautot and Faivre,
2017). As sample size is big so doing experimental study will consume more time and cost. The
outcomes obtained will not be relevant and proper. Thus, due to it this design is not used. Now,
inferential analysis method is used to solve question. It is identified that problem can be solved
using supervised learning. In this it is easy to gather data that is already labelled. Beside,
previous data can also be taken into consideration. So, in present report these both methods is
suitable because it will be useful in gathering relevant data.
Descriptive Statistics
Mean Std. Deviation N
unitpricebasedonweightofraw
material 1.2333 .43018 30
typeofshipmentmodeisoftenu
sedbyvendors 1.8333 .79148 30
Correlations
unitpricebasedo
nweightofrawmat
erial
typeofshipmentm
odeisoftenusedby
vendors
Pearson Correlation
unitpricebasedonweightofraw
material 1.000 -.591
typeofshipmentmodeisoftenu
sedbyvendors -.591 1.000
6

Sig. (1-tailed)
unitpricebasedonweightofraw
material . .000
typeofshipmentmodeisoftenu
sedbyvendors .000 .
N
unitpricebasedonweightofraw
material 30 30
typeofshipmentmodeisoftenu
sedbyvendors 30 30
Model Summaryb
Model R R Square Adjusted R
Square
Std. Error of the
Estimate
Change Statistics
R Square
Change
F Change df1
1 .591a .349 .326 .35323 .349 15.012 1
Model Summaryb
Model Change Statistics Durbin-Watson
df2 Sig. F Change
1 28a .001 1.241
a. Predictors: (Constant), typeofshipmentmodeisoftenusedbyvendors
b. Dependent Variable: unitpricebasedonweightofrawmaterial
ANOVAa
Model Sum of Squares df Mean Square F Sig.
1
Regression 1.873 1 1.873 15.012 .001b
Residual 3.494 28 .125
Total 5.367 29
a. Dependent Variable: unitpricebasedonweightofrawmaterial
b. Predictors: (Constant), typeofshipmentmodeisoftenusedbyvendors
7

Coefficientsa
Model Unstandardized Coefficients Standardized
Coefficients
t Sig.
B Std. Error Beta
1
(Constant) 1.822 .165 11.039 .000
typeofshipmentmodeisoftenu
sedbyvendors -.321 .083 -.591 -3.875 .001
a. Dependent Variable: unitpricebasedonweightofrawmaterial
Residuals Statisticsa
Minimum Maximum Mean Std. Deviation N
Predicted Value .8587 1.5009 1.2333 .25414 30
Residual -.50092 .49908 .00000 .34709 30
Std. Predicted Value -1.474 1.053 .000 1.000 30
Std. Residual -1.418 1.413 .000 .983 30
a. Dependent Variable: unitpricebasedonweightofrawmaterial
Interpretation – It is analyzed that the significant value P= obtained is .001 which is less than
P= 0.05. it means that there is no relationship between unit price of raw materials and type of
shipment method used by suppliers. Here, null hypothesis is accepted. The vendors charge
similar price in all shipment mode. There is only slight difference in price of shipment.
Regression
Descriptive Statistics
Mean Std. Deviation N
Aldivendorsmaintainpriceand
costatminimumlevel 1.4333 .50401 30
unitpriceremainssamethroug
hentiresupplychain 1.5667 .50401 30
8

Correlations
Aldivendorsmain
tainpriceandcost
atminimumlevel
unitpriceremainss
amethroughentire
supplychain
Pearson Correlation
Aldivendorsmaintainpriceand
costatminimumlevel 1.000 -.050
unitpriceremainssamethroug
hentiresupplychain -.050 1.000
Sig. (1-tailed)
Aldivendorsmaintainpriceand
costatminimumlevel . .397
unitpriceremainssamethroug
hentiresupplychain .397 .
N
Aldivendorsmaintainpriceand
costatminimumlevel 30 30
unitpriceremainssamethroug
hentiresupplychain 30 30
Model Summaryb
Model R R Square Adjusted R
Square
Std. Error of the
Estimate
Change Statistics
R Square
Change
F Change df1
1 .050a .002 -.033 .51229 .002 .070 1
Model Summaryb
Model Change Statistics Durbin-Watson
df2 Sig. F Change
1 28a .794 3.108
a. Predictors: (Constant), unitpriceremainssamethroughentiresupplychain
b. Dependent Variable: Aldivendorsmaintainpriceandcostatminimumlevel
ANOVAa
9

Model Sum of Squares df Mean Square F Sig.
1
Regression .018 1 .018 .070 .794b
Residual 7.348 28 .262
Total 7.367 29
a. Dependent Variable: Aldivendorsmaintainpriceandcostatminimumlevel
b. Predictors: (Constant), unitpriceremainssamethroughentiresupplychain
Coefficientsa
Model Unstandardized Coefficients Standardized
Coefficients
t Sig.
B Std. Error Beta
1
(Constant) 1.511 .310 4.873 .000
unitpriceremainssamethroug
hentiresupplychain -.050 .189 -.050 -.264 .794
a. Dependent Variable: Aldivendorsmaintainpriceandcostatminimumlevel
Residuals Statisticsa
Minimum Maximum Mean Std. Deviation N
Predicted Value 1.4118 1.4615 1.4333 .02509 30
Residual -.46154 .58824 .00000 .50338 30
Std. Predicted Value -.860 1.124 .000 1.000 30
Std. Residual -.901 1.148 .000 .983 30
a. Dependent Variable: Aldivendorsmaintainpriceandcostatminimumlevel
Interpretation – by analysing the above table it is evaluated that the significant value obtained
is P= .794 that is more than P= 0.05. So, alternate hypothesis is accepted. It means that Aldi
vendors are able to maintain same price of goods and its unit price as well. Moreover, even with
change in unit price suppliers are able to maintain same level of price until product is delivered
to customers. It has enabled in generating delivery it on time and at low cost.
10

T test
One-Sample Statistics
N Mean Std. Deviation Std. Error Mean
typeofshipmentmodeisoftenu
sedbyvendors 30 1.8333 .79148 .14450
unitpricebasedonweightofraw
material 30 1.2333 .43018 .07854
theredifferenceinpackpricean
dunitprice 30 1.4000 .49827 .09097
typeofshipmentmodeisspeed
yandincurlesscost 30 1.8667 .77608 .14169
freightcostdependsonweighto
frawmaterial 30 1.4667 .50742 .09264
Aldivendorsmaintainpriceand
costatminimumlevel 30 1.4333 .50401 .09202
unitpriceremainssamethroug
hentiresupplychain 30 1.5667 .50401 .09202
One-Sample Test
Test Value = 0
t df Sig. (2-tailed) Mean Difference 95% Confidence
Interval of the
Difference
Lower
typeofshipmentmodeisoftenu
sedbyvendors 12.687 29 .000 1.83333 1.5378
unitpricebasedonweightofraw
material 15.703 29 .000 1.23333 1.0727
theredifferenceinpackpricean
dunitprice 15.389 29 .000 1.40000 1.2139
typeofshipmentmodeisspeed
yandincurlesscost 13.174 29 .000 1.86667 1.5769
freightcostdependsonweighto
frawmaterial 15.832 29 .000 1.46667 1.2772
Aldivendorsmaintainpriceand
costatminimumlevel 15.577 29 .000 1.43333 1.2451
11

unitpriceremainssamethroug
hentiresupplychain 17.026 29 .000 1.56667 1.3785
One-Sample Test
Test Value = 0
95% Confidence Interval of the Difference
Upper
typeofshipmentmodeisoftenusedbyvendors 2.1289
unitpricebasedonweightofrawmaterial 1.3940
theredifferenceinpackpriceandunitprice 1.5861
typeofshipmentmodeisspeedyandincurlesscost 2.1565
freightcostdependsonweightofrawmaterial 1.6561
Aldivendorsmaintainpriceandcostatminimumlevel 1.6215
unitpriceremainssamethroughentiresupplychain 1.7549
Interpretation – from above table it is analysed that the significance value is 0.000 which is less
than P= 0.05. thus, there is difference is mean value of variables. but mean value do not differ to
large extent.
Correlation
Descriptive Statistics
Mean Std. Deviation N
typeofshipmentmodeisoftenu
sedbyvendors 1.8333 .79148 30
unitpricebasedonweightofraw
material 1.2333 .43018 30
theredifferenceinpackpricean
dunitprice 1.4000 .49827 30
typeofshipmentmodeisspeed
yandincurlesscost 1.8667 .77608 30
freightcostdependsonweighto
frawmaterial 1.4667 .50742 30
Aldivendorsmaintainpriceand
costatminimumlevel 1.4333 .50401 30
unitpriceremainssamethroug
hentiresupplychain 1.5667 .50401 30
12

Correlations
typeofshipment
modeisoftenuse
dbyvendors
unitpricebasedo
nweightofrawmat
erial
theredifferencein
packpriceandunit
price
typeofshipmentmodeisoftenu
sedbyvendors
Pearson Correlation 1 -.591** .262
Sig. (2-tailed) .001 .161
N 30 30 30
unitpricebasedonweightofraw
material
Pearson Correlation -.591** 1 .193
Sig. (2-tailed) .001 .307
N 30 30 30
theredifferenceinpackpricean
dunitprice
Pearson Correlation .262 .193 1
Sig. (2-tailed) .161 .307
N 30 30 30
typeofshipmentmodeisspeed
yandincurlesscost
Pearson Correlation .524** -.007 .321
Sig. (2-tailed) .003 .971 .084
N 30 30 30
freightcostdependsonweighto
frawmaterial
Pearson Correlation .114 .116 .191
Sig. (2-tailed) .547 .542 .312
N 30 30 30
Aldivendorsmaintainpriceand
costatminimumlevel
Pearson Correlation -.072 .154 -.165
Sig. (2-tailed) .705 .417 .384
N 30 30 30
unitpriceremainssamethroug
hentiresupplychain
Pearson Correlation -.187 .005 .027
Sig. (2-tailed) .322 .978 .885
N 30 30 30
Correlations
typeofshipmentm
odeisspeedyandi
ncurlesscost
freightcostdepend
sonweightofrawm
aterial
Aldivendorsmainta
inpriceandcostatm
inimumlevel
typeofshipmentmodeisoftenus
edbyvendors
Pearson Correlation .524 .114** -.072
Sig. (2-tailed) .003 .547 .705
N 30 30 30
unitpricebasedonweightofraw
material
Pearson Correlation -.007** .116 .154
Sig. (2-tailed) .971 .542 .417
13

N 30 30 30
theredifferenceinpackpriceand
unitprice
Pearson Correlation .321 .191 -.165
Sig. (2-tailed) .084 .312 .384
N 30 30 30
typeofshipmentmodeisspeedy
andincurlesscost
Pearson Correlation 1** .251 -.200
Sig. (2-tailed) .181 .290
N 30 30 30
freightcostdependsonweightofr
awmaterial
Pearson Correlation .251 1 .126
Sig. (2-tailed) .181 .508
N 30 30 30
Aldivendorsmaintainpriceandc
ostatminimumlevel
Pearson Correlation -.200 .126 1
Sig. (2-tailed) .290 .508
N 30 30 30
unitpriceremainssamethroughe
ntiresupplychain
Pearson Correlation .112 .279 -.050
Sig. (2-tailed) .557 .136 .794
N 30 30 30
Correlations
unitpriceremainssamethroug
hentiresupplychain
typeofshipmentmodeisoftenusedbyvendors
Pearson Correlation -.187
Sig. (2-tailed) .322
N 30
unitpricebasedonweightofrawmaterial
Pearson Correlation .005**
Sig. (2-tailed) .978
N 30
theredifferenceinpackpriceandunitprice
Pearson Correlation .027
Sig. (2-tailed) .885
N 30
typeofshipmentmodeisspeedyandincurlesscost
Pearson Correlation .112**
Sig. (2-tailed) .557
N 30
freightcostdependsonweightofrawmaterial
Pearson Correlation .279
Sig. (2-tailed) .136
N 30
Aldivendorsmaintainpriceandcostatminimumlev
el
Pearson Correlation -.050
Sig. (2-tailed) .794
N 30
14

unitpriceremainssamethroughentiresupplychai
n
Pearson Correlation 1
Sig. (2-tailed)
N 30
**. Correlation is significant at the 0.01 level (2-tailed).
Interpretation- it is analyzed from above that the significant value is – .591 that is less than P=
0.05. so, it is identified that there is difference in mean value of variables.
Anova test
ANOVA
Sum of Squares df Mean Square F
unitpricebasedonweightofraw
material
Between Groups 2.450 2 1.225 11.340
Within Groups 2.917 27 .108
Total 5.367 29
theredifferenceinpackpricean
dunitprice
Between Groups .923 2 .461 1.985
Within Groups 6.277 27 .232
Total 7.200 29
ANOVA
Sig.
unitpricebasedonweightofrawmaterial
Between Groups .000
Within Groups
Total
theredifferenceinpackpriceandunitprice
Between Groups .157
Within Groups
Total
Interpretation – by analysing the table it is stated that significant value P= .157 that is more
than P= 0.05. it means null hypothesis is accepted. The difference between unit and pack
depends on weight of raw material. So, when weight increases there is change in unit price.
15

Similarly, pack price also varies with change in weight. Therefore, difference between unit and
pack price depends on weight of raw material.
It is evaluated that unit price of raw material does not depend on type of shipment. This is
because in all type air, road, rail, etc. unit price depends on weight of raw material. Furthermore,
P value is.001 which is less than P= 0.05. However, price depend on distance and weight.
Usually, in shipment unit price are similar. The price varies only when weight is increased or
decreased. Moreover, significant value obtained is P= .794 that is more than P= 0.05. it states
that Aldi suppliers are able to maintain unit price of goods through overall delivery of products.
It has helped in keeping prices at low level and speedy delivery of goods. Also, vendors are
playing vital role in reducing expenses of Aldi supply chain. besides this, it is analysed that
significant value P= .157 that is more than P= 0.05. The difference between unit and pack
depends on weight of raw material. So, when weight increases there is change in unit price.
Similarly, pack price also varies with change in weight. (McNeish and Harring, 2017). In t test
the significance value is 0.000 which is less than P= 0.05. thus, there is difference is mean value
of variables. but mean value do not differ to large extent. In anova, significant value is – .591
that is less than P= 0.05. so, it is identified that there is difference in mean value of variables.
However, the organisation can apply those outcomes to reduce cost of supply chain. By
reducing weight of raw materials to be supplied, cost can be decreased. Along with it, by
selecting only limited locations, vendors can be integrated. Likewise, there is no difference in
unit and pack price. It changes due to change in weight. Therefore, cost of suppling goods
increases. So, in order to minimise cost, business can maintain weight of raw materials. The unit
and pack size can be same. For that, technology can be used. The company can implement block
chain technology is supply chain. It will be easy in maintaining record and data of products. In
addition to it, by keeping same weight in supply chain, Aldi can reduce its expenses. Another
suggestion that can be followed is if goods to be supplied are in more quantity than business can
use different shipment ways. It will enable in maintaining cost incurred at fix rate. Other than it,
goods can be delivered within specified time. Thus, these are the suggestions that can be
followed by Aldi to reduce cost of supply chain.
By evaluating report, it is observed that use of inferential statistics relationship was
identified between dependent and independent variables. but the model is not effective as it only
interrelates some variables. Furthermore, results obtained are not proper as well. Also, the data
16

gathered is only from 30 suppliers which is not enough to answer research question. In addition,
many elements are missing that is distance, profit, practices, etc. and most data gathered is
delivery date, schedule, supplier location, etc. hence, it does not relate with business question.
Moreover, there are certain limitation as well of data (Montgomery, 2017). The data and
information do not include authentic source. The suppliers are selected randomly and no proper
location or region is determined. So, in order to develop more formal report, data can be
gathered from vendors of particular location. Apart from it, some secondary data could also been
gathered to give insight about what practices are previously applied. There should have some
criteria set on basis of which data can be gathered.
DEPLOYMENT ETHICS AND CONCLUSION
Deployment risk include performance risk. in this due Aldi supply chain performance can
be impacted. It may result in failure of project and leading to inconsistencies in supply chain.
Another risk is it may require high cost in implementing project. However, project may not be
implemented on time. it may result in delay in implementation. Therefore, business may not be
able to manage supply chain. The project should not be deployed in organisation. It is because
outcomes do not contain any specific strategy or practice that can be used. due to these risks
project should not be deployed. (Paradis, O'Brien and Martimianakis, 2016)
There are some ethical consideration and risks related to project. it includes lack of
storing of data and information. the data privacy may be breached.
It can be summarised that Aldi needs to identify that what strategies and practices are
followed by suppliers in supply chain. Also, the cost of supplying raw materials is same in all
shipment method. But change in unit and pack price depends on weight of goods to be supplied.
There are some suggestions that can be used by Aldi. the organisation can implement block chain
technology. It will be useful for them to maintain record of data in effective way. Moreover, cost,
time, unit and pack price can be easily maintained and updated with help of block chain
technology.
Limitations
The limitation of report is that many variables are considered. For example – cost
incurred by vendor, profit earned, etc. also, research gap is not identified and in data collected
the things included is schedule, date of delivery, etc. that is of no use. The outcomes do not
provide a satisfactory answer to business question (Liu, Yin and Blanas, 2019)
17

Suggestion
In future there are some suggestion that can be followed:
First is by taking data of suppliers which include distance, time, etc. which will be useful in
relating with outcomes. This will give overview of how much time and cost each supplier
consume.
Another is along with profit, strategies and practices can also be included in future study.
It will help in determining those suppliers where more cost is incurred.
Some secondary data can also be included in future research. This will be easy to find out gap
and then target area.
The research can be conducted on particular practice that is technology. It will be easy to
find out whether use of technology can help in reducing cost in supply chain.
Apart from it, other variables such as total cost incurred, profit, variable cost, etc. therefore, in
future research these variables can be used and identified. It will provide in depth and detailed
information related to how cost can be reduced in supply chain.
18

REFERENCES
Books and journals
Antons, D. and Breidbach, C.F., 2018. Big data, big insights? Advancing service innovation and
design with machine learning. Journal of Service Research, 21(1), pp.17-39.
Barday, K.A., OneTrust LLC, 2018. Data processing and communications systems and methods
for the efficient implementation of privacy by design. U.S. Patent Application 10/102,533.
Bimonte, S., Sautot, L. and Faivre, B., 2017. Multidimensional model design using data mining:
A rapid prototyping methodology. International Journal of Data Warehousing and
Mining (IJDWM), 13(1), pp.1-35.
Dong, J., Ma, C. and Xin, L., 2017, March. Data augmented design: Urban planning and design
in the new data environment. In 2017 IEEE 2nd International Conference on Big Data
Analysis (ICBDA)( (pp. 508-512). IEEE.
Hsu, Y.L. and Kuo, Y.C., 2017. Design and implementation of a smart home system using
multisensor data fusion technology. Sensors, 17(7), p.1631.
Kim, N.W., Schweickart, E. and Pfister, H., 2016. Data-driven guides: Supporting expressive
design for information graphics. IEEE transactions on visualization and computer
graphics, 23(1), pp.491-500.
Liu, F., Yin, L. and Blanas, S., 2019. Design and evaluation of an rdma-aware data shuffling
operator for parallel database systems. ACM Transactions on Database Systems
(TODS), 44(4), pp.1-45.
McNeish, D.M. and Harring, J.R., 2017. Clustered data with small sample sizes: Comparing the
performance of model-based and design-based approaches. Communications in Statistics-
Simulation and Computation, 46(2), pp.855-869.
Montgomery, D.C., 2017. Design and analysis of experiments. John wiley & sons.
Paradis, E., O'Brien, B. and Martimianakis, M.A., 2016. Design: selection of data collection
methods. Journal of graduate medical education, 8(2), pp.263-264.
Varley, J.B., Miglio, A. and Hautier, G., 2017. High-throughput design of non-oxide p-type
transparent conducting materials: Data mining, search strategy, and identification of
boron phosphide. Chemistry of Materials, 29(6), pp.2568-2573.
19

Appendix
Survey 1
Q-1 What type of shipment mode is often used by vendors?
Air
Road
Rail
Q-2 Is unit price based on weight of raw material?
Yes
No
Q-3 Is there difference in pack price and unit price?
Yes
No
Q-4 Which type of shipment mode is speedy and incur less cost
Air
Road
Rail
Q-5 Does freight cost depends on total weight of raw material?
Yes
No
Q-6 Are Aldi vendors able to maintain price and cost at minimum level?
Yes
No
Q-7 Does unit price remains same through entire supply chain?
Yes
No
20

Survey 2
Q-1 What mode of shipment incur less cost in delivery of products?
Air
Truck
Q-2 Is offering discount to customers increases delivery cost for supplier?
Yes
No
Q-3 Does supplying large number of quantities decrease cost of supplier?
Yes
No
Q-4 Can sales be increased by changing shipment way of delivering goods?
Yes
No
21