Data Handling and Decision Making

This report discusses data gap analysis, data preparation, and big data infrastructure development. It also explains how big data analytics can be used in organizational decision making. The report provides recommendations for improving data quality and reorganizing data-driven processes. It also examines the process of data collection, filtering, and integration, and discusses the limitations of integrated datasets.

Data Handling and
Decision Making

Contents
EXECUTIVE SUMMARY.............................................................................................................4
TASK 1............................................................................................................................................5
1.1Performing data gap analysis for an organisation...................................................................5
Identifying data sources and data sets available for the project..................................................5
Inspection of data integrity and potential gaps in data analytics and data protection.................5
TASK1.2..........................................................................................................................................6
Recommended improvements to the data on project data analytics............................................6
Reorganisation of the current data driven processes to enhance data analytics and decision
making process............................................................................................................................6
Elaborating the roadmap for the development or enhancement of big data infrastructure..........7
Compliance of the proposed changes in the data analytics.........................................................8
1.3 Explaining how the proposed big data analytics can be used in the organisational decision
making.........................................................................................................................................9
REFERENCES..............................................................................................................................10
PART 2.1.......................................................................................................................................12
Explain process of data preparation that includes describing data collection, filtering and
integration procedure. And examine the data representatives along with statement of
generalisability and include limitation of integrated dataset as well.........................................12
TASK 2.2.......................................................................................................................................14
TASK 2.3.......................................................................................................................................19
Present further outcomes, for supporting the decisions made under above task.......................19
TASK 2.4.......................................................................................................................................20
Give recommendation on the implementation, acceptance and assessment of the decision
along with discussing that how it contributes to strategic management....................................20
REFERENCES..............................................................................................................................21

EXECUTIVE SUMMARY
Data gap analysis is kind of analysis in which the analysts make use of the different tools to
sort the data in more convenient manner which would help them to interpret and take various
decisions related to the case in question. The following report highlights the case of data gap
analysis of a Community proposal. Various recommendations are being provided to the
organisation. Different types of decisions are also being discussed herein the report. The
advantage of data analysis in the helping the stakeholders to take a decision has also been
discussed. A detailed roadmap related to the big data infrastructure has also been provided in the
report.

TASK 1
1.1Performing data gap analysis for an organisation
Background of the organisation: This project deals in the community proposals which abide the
principle of charity and donation. It includes the activities related to the welfare and those
activities does not result into the profits but increase the economic growth of the country. Every
country become complete by its people only. There are various examples of community
proposals such as neighbourhood associations, government and non-profit organisations. It
serves various sectors of the economy such as old people, children, disabled, animals and
surroundings. For instance, a Christmas supper for the homeless (Levings and Stewart). These
community projects based on rural and urban areas helps to solve the disputes and issues of the
society which reduces the scope of conflict among the people of society.
Identifying data sources and data sets available for the project.
Meaning – Data source is a location from where the data originates. It can be either in the
primary or secondary form. The primary data is first hand and more accurate than other forms of
data. Whereas Secondary data is taken from the magazines, journals and newspaper.
Data set – It refers to the set of one or more records. It contains the same class of data. This data
set contains the information about number of people residing in the country and employment &
unemployment details of the country.
Inspection of data integrity and potential gaps in data analytics and data protection
Data integrity – It shows the validity or accuracy within the data. This term indicates the
reliability of the data which means when the data is used for several times, it will give the same
result every time. The integrity of the data can be calculated by following all the legislations
formed by the government of UK. The gap can be due to the various reasons such as Data
literacy, machine learning and analytics (Biswas, Sachdeva and Tortajada, 2021).
Data analytics – it is the branch of science which helps in making interpretations by using the
raw data collected earlier.
Data protection – It is the process of safeguarding the raw form of data from corruption,
compromise and various other forms of data loss.

TASK1.2
Recommended improvements to the data on project data analytics.
The recommendation for improving the quality of the data can be gained by various
measures such as controlling more variables, reducing the biases of sample and increasing the
number of sample size which helps to relate with the entire population.
Reorganisation of the current data driven processes to enhance data analytics and decision
making process.
Number Data source Specific organisational
decision
Decision type
1 Market research The main aim is to
satisfy the customer
segment which require
studying the trends of
market.
Strategical
2 Determination of key
performance indicators
Creating a mind map
and flow chart.
Tactical
3 Quality control. Inspecting quality
standards and
complying staff
requirements.
Operational
The reorganisation of current data is helpful in sorting the data according to the desired
responses. There are various decisions which are related to operations and finance of the
organisation. Analysis of data helps in the taking smarter decisions of the organisation. The
decisions are taken by the top level managers or higher authorities. If choices made by the
management are in favour of the enterprise, it will lead to the improved productivity and result in
efficient operations of the organisation. There is a term known as predictive analysis, it uses
segmentation, forecasting, pricing and customer satisfaction.

Elaborating the roadmap for the development or enhancement of big data infrastructure
Number Phases of the big data analytic
process
Activities to be implemented
in organisation
1 Turning needs of organisation
into objectives.
It includes translating main
aim of the organisation into
framing plans. It would be
possible by taking 360
customer view, predictive
maintenance or inventory
optimization
2 Designing big data architecture It identifies the source of data
i.e., from where the data
comes from. This phase keeps
check on the flow of data.
3 Integration of big data with
different applications and
systems.
This phase includes the input
of valuable data. For
benefiting from synergy and
leveraging, it is necessary to
identify the specific
applications with the data is
merged.
4 Working on quality of the data This stage consists of
improving the quality of the
data by improving reliability
of the data. The 5 vs of big
data are required to be
followed value, velocity,
veracity, volume and variety.
5 Turning design into code With the use of machine

learning codes and artificial
intelligence, the data in
translated into code.
Compliance of the proposed changes in the data analytics.
Number Data protection/
Ethics
requirement
Procedures to be
implemented in
the chosen
organisation or
project
Relevant
data
protection
standard
References to
literature
1 Data integrity The application of
tools for checking
the validity and
accuracy.
Domain integrity
and entity
integrity.
(What is Data
Integrity and Why
Is It Important?,
2022)
2 Audit trail for
data
The verification
of the data is
done.
Audit command
language.
(Why You Need a
Data Audit Trail?,
2022)
3 Quality assurance Checking the
quality of each
activity or
product.
Cause effect
diagram
(What is Quality
Assurance(QA)?
Process, Methods,
Examples, 2022.)
4 Confidentiality of
data.
Transparency in
ethical norms for
conducting
confidentiality.
Managing data
access.
(Managing data
confidentiality,
2022. )

1.3 Explaining how the proposed big data analytics can be used in the organisational decision
making.
Business decisions – Any choice made by the management or top level managers to fulfil the
goals, future activities and mission of the enterprise is known as business decision making
process.
Business decision Decision type
The plans made by the top levels mangers for
determining the goals and objective for the
organisation. The modern tools of the big data
help to identify the pattern of consumption by
the existing market segment and helps to frame
the strategic plans of the enterprise.
Strategic
The tactical decisions involve breaking long
term goals into short term goals. The big data
helps to
Tactical
Operational plans refer to the activities
conducted on daily basis to carry out the
objectives of the enterprise.
Operational

REFERENCES
Biswas, A.K., Sachdeva, P.K. and Tortajada, C., 2021. Gap Analysis of Four Domains.
In Phnom Penh Water Story (pp. 89-90). Springer, Singapore.
Levings, C.D. and Stewart, H.L., Research Priorities for Nearshore Algae in Coastal British
Columbia Workshop and Gap Analysis-Final Report.

EXECUTIVE SUMMARY
The decision that would help in analysis is Regression analysis and SPSS method must be
chosen for evaluating. It also helps to understand its importance and necessity in a project plan or
company that would help to predict the dependency of one value of variable on another variable.
It is thus observed that Urban community must hire employees who specialise in SPSS and are
having a thorough knowledge of it for better results. It is further advised to that the company to
schedule proper training for people who can perform better and serve as an asset for the same.

PART 2.1
Explain process of data preparation that includes describing data collection, filtering and
integration procedure. And examine the data representatives along with statement of
generalisability and include limitation of integrated dataset as well.
Data collection can be explained as a process suggested for collecting, sorting and
examining the information accurately for carrying out research with the help of standardised
tools, methods and techniques. An organisation or a person that conducts the research can
evaluate hypothesis on basis of data collected. The first step for initiating any type of research is
to gather the data at one place (Egger, 2022). The necessary aspect that must be kept in mind is
reliability and accuracy present in the information collected also how it contributes in decision
making as well. There are two kinds of methods applied in such data such as primary and
secondary. In current scenario there are different methods for collection of primary data. It can
be collected with the help of interviews scheduled on telephonic conversations, in person
conversation or through emails as well. The secondary data can be gathered at one place through
sources such as journals, newspaper, articles, books and their websites as well. But the credibility
of such sources is dependent on people who has collected it in initial stages. After collection of
information from efficient sources, it is necessary to sort & filter this information for evaluating
it.
Filtering of data can be explained as an operation for choosing specific section of content
for further investigation. This portion is distributed on a temporary basis in few cases and on
permanent basis in others, but the whole set further is kept with them only. For instance, there is
a need to collect data about a particular duration. So, filtering of data is demanded that would
help to sort data as well for a given time period. It is also helpful for computation of outcome
that is required to be sorted. After filtration and sorting of useful information next step that is
needed is to integrate the data that is diffused under different formats.
Data integration can be explained as a method that helps to put all information collected
from various sources and merging it in a single file or presenting it in a respective frame. It starts
from the procedure based on activities such as mapping, transforming and cleansing. It further
helps to make tools effective that related to analytics and will be helpful for implementation of
decisions as well (Fedushko and Ustyianovych, 2019). There is no such method that is soleus

made for integration of data. In this process, client requests the server for providing useful data
needed. The server then focuses on collection of data needed by it on basis of external as well as
internal sources. Once the useful data is collected it is united at a common place under one
research report. After the completion of report prepared so far it can be provided to the user who
is in need of it and thus fulfil the requirements accordingly. It is necessary to analyse big data
and solve the challenging & barriers coming on the way in handling such vast data. It helps to
manage large velocity & volume of figure collected so far from different sources for example
website, social media platforms, content generated through machine and many others (Silveira
and et.al., 2021). After integration it is mandatory for them to have a proper analysis of its
representatives as well.
Representatives can be defined as a base that helps to have a comparison of actual data
with actual conditions that are being acknowledged during investigation. Representative sample
can be explained as a group that is chosen from laid down option of a wide range of population
that flex big unit that has been chosen for study. Such process is not a simple task the reason
being it is a complex activity to assess the group that is related to the one that is demanded by the
expert. It can be the event that takes place at the time of action of copying, it might be possible
that the researcher might become biased or reflect duplication. There is certain basis that might
be counted as reason for such replication as in case of age, profession, gender, ownership or
illness. It is dependent on the range of study and data that is being needed by the person.
Generalisability can be explained as an extension of conclusions and research of work
carried out. It takes in account the forecasting that is done on the basis of experiences recorded
by a user on a daily basis. It further predicts that if a certain event or activity has taken place
multiple times there is a possibility that it might occur in future time as well. It analyses the
behaviour that relates to the content collected and make an effort to generalise it in related
condition (Raikov, 2020).
Data integration can be explained as a process that involves many uses which makes it
comparatively easier than others to apply in case of big data but has many limitations associated
with it. Therefore, it is not possible to keep all data from which the data integrated has been
driven. It comes across many issues and problems in the process of integration of data from
different sources. It further doesn't provide any surety towards the information is stored at a

secure and safe place or not. It can be considered as a reliable and accurate source for decision
making.
TASK 2.2
It is a method which is used to investigate the information of objects and their relationship with
different article. It is basically used to derive the information need for the business process.
Managers can optimise internal business operations, evaluate and monitor emerging risks,
establish system for the ongoing feedback and identity new consumer’s trends and also improve
the services by incorporating data analytics into core strategies to take actions for the
improvement (Abbasian and et.al., 2018). The information is used to be assemble at one place in
order to analyse the data set. Managers have to see every aspect from both the sides because of
the dynamic environment of the business. Businesses have to deal with huge risk and reward
which is directly proportional in nature. Secondly, they need to have involve data analytics into
their decision-making process.
Selection of machine learning and also justify the machine learning based on the objectives.
Main goal of the case study is to make a decision on the basis of different tests of
statistics. Machine learning models is applied with the big data which helps in descriptive,
prescriptive and predictive analysis and simulation:
 By finding the missing values various tests are performed.
 The values so derived is used in predictive analysis which is performed in order to find
out correlation and regression.
 Data is collected and stored in cloud warehouses, then the segmented content is
performed on the basis of subject, region, state and products category.
 If the content which is given is general then, prescriptive analysis will be performed in
order to find out he missing figures.
1. Regression Analysis: It is a technique which is used to estimate relationship between a
dependent factor and one or more independent factor. It is utilised to ascertain the
strength of the relationship between the variables. The method involved in performing
regression helps in determining the variables which affects the study of variable that how
a variable matters and how it impact on another variable (Henares and et.al., 2019).

The point here is to decrease the number of predictive variables in respect of those which are
critical and represents a close relation with the variable which is represented by a complete set.
Variables are selected on the basis of dependent and independent variables, that considers
developing of indicators while concerning with explicit indicator variables. There is always a
choice of deciding a variable in studying the relationship between these factors. It also helps in
studying the impact of one variable on another (Jadhav and Kadam, 2020).
It is justified with responses which are basically related to the set of inputs. Linear model is
convenient to comprehend and fit in the observation of data.
2. Correlation: In carrying out research, it is a technique which is used find the direct
relationship between the two factors. A high correlation means that the relation with both
the variables is pretty strong. It also studies change in one variable with the other variable
remains the same.
Statistical surveying helps in use of scientific method of examining quantitative information
which is gathered through different research techniques such as live surveys and studies. It helps
in recognising the relationship, pattern and design between the two data sets or factors. If one
variable increases with the increase in the other variable, then it is termed as positive connection.
3. Annova: It is one of the statistical techniques which is used to determine the difference
between the self-reliant variable and dependent factor which have two or more varieties.
These includes following types of Annova:
 One-way Annova: It only have one independent variable.
 Two way Annova: It has two independent variables which is used to study the
relationship between the two variables (Potapov and et.al., 2021). It defines that its
connection is not uniform across the factors. It confirmed by confirming the impact of
one or more factors by comparing various data.
Table 1. Compare between different inferential statistical models.
Tests or models Advantages Limitations References to
literature.
1 Correlation Non of the
variables got
manipulated by
researchers.
It is not able to
determine the
variable which
influence the
12 Advantages
and disadvantages
of correlation
research studies,

most. 2022
https://
vittana.org/12-
advantages-and-
disadvantages-of-
correlational-
research-studies
2 ANNOVA It increases
statistical power
and reduces
random
variability.
After controlling
the first variable,
the effect of it can
be seen on the
second variable.
In any case if null
hypothesis is
rejected, there is
at least one group
which differs
from other.
Assumptions
need to be
fulfilled which
generally lacks in
Annova.
Annova, 2018
https://
clinfowiki.org/
wiki/index.php/
ANOVA
3 Regression It is very easily
understandable as
it is built with
statistical
principles such as
least square error
and correlation.
This model
includes every
aspect of a model
which are
It does not
consider non
linearity, user
have to take care
of the the
requirement of
the brief and and
additional
information
required to be
studied.
Advantages and
Disadvantages of
Regression
Model, 2022
https://
www.vtupulse.co
m/machine-
learning/
advantages-and-
disadvantages-of-

required. regression-model/
Use of statistical tools like Excel, SPSS, Weka to the model in the report and reporting the
potential outcomes related to modelling:
There are different statistical tools which can be used in the excel and SPSS software.
These tools are average, mode, median, standard deviation, correlation, regression etc. The
learning models which have been discussed above like the Regression, ANNOVA and the
correlation model are considered. And with the help of these, outcomes are calculated which help
in the reporting of the model (Balasubramani and Dodagoudar, 2022).
Excel is a spreadsheet program which consists of different tables where the analysts can make of
the tables to present the raw data into these sheets. It looks simple and this major simplicity of
the program allows it to be used by different people for their own purpose. There are different
tools and formulas which can be used by the analysts like sum, standard deviation, average,
variance which helps in interpreting this raw data and make conclusions from the same.
SPSS is a crucial program which have been made to help the analysts. This program helps in
dissecting the logical information which is related to the study. SPSS is an acronym for
Statistical Package for Social Sciences (SPSS). It is programming tool which determines the
major information related to the data presented in the input sheet. This information which has
been taken out is used in the survey of the market, data mining, and suggesting different
conclusions for the same.
SPSS has been made in such a way that it can present enormous amount of data set in the
variable sheet of the software. The software consists of mainly two sheet, data sheet and variable
sheet. The data sheet consists the major information related to the variables and the variable
sheet consists all the numerical and the variables which are necessary for the study that is being
conducted (Büttner and et.al., 2019). The measurable data in the data set helps the analysts to
check the demand for a product or service in the market and can provide required
recommendations to the producers. It uses required index for an information to deliver the
appropriate results in the market (Franks, 2018).
Regression is another technique which is used in the SPSS or excel. To use this technique, the
analysts are required to go to the analyse tab and select the regression variable. After this, many
ways to calculate the regression in the SPSS pops up. The analysts are required to choose the

most appropriate way of calculation using the data set which is linear. The variables are required
to be segregated in the dependent and independent variables and put in the same boxes. The
dependent and independent variable can be explained with the help of an example, the price is
considered as the dependent variable on the demand and the supply of the goods and services.
The income is considered as an independent variable (Jiang and et.al., 2019).
ANNOVA: this tool is used in the SPSS to check the differences that are there in the mean
values of the dependent variable in relation to the controlled independent variable. These are
considered after the effects of uncontrolled independent variable.
An ANOVA test is a way to find out if examination or inquiry results are momentous. In other
words, they help you to illustration out if you need to reject the null hypothesis or accept the
alternate hypothesis. Basically, you're experimenting groups to see if there's a quality between
them. As far as SPSS is concerned, ANNOVA is considered as one of the important test which
checks the means for a two or more population in the study. In SPSS, ANNOVA has to have a
dependent variable which forms the metric, which is measured with the help of interval or the
ratio scale. The ANOVA in the SPSS needs one or more independent variable which is required
to be categorical. These variables refer to a factor in the SPSS ANOVA.
Weka includes a combination of visualization tools and algorithms for data investigating
modelling, jointly with graphical user program for easy access to these mathematical
relations. The original non-Java version of Weka was a Tcl/Tk front-end to (mostly third-party)
moulding algorithms enforced in other programing languages, plus data secondary in C, and
a make file-based system for moving machine acquisition research.
The decisions based on the above outcomes:
With the above mentioned outcomes, many decisions can be taken after a detailed and
critical analysis. It can be said that the Urban Community may use the regression analysis to
critically analyse the different data which has been collected by the analysts and make the
required interpretations from the same (Madhavrao and Moosakhanian, 2018). This regression
analysis is used to measure the relation between the different variables present in the study. This
measures the degree with which one variable is dependent on the other and what is the
relationship between them. The independent variable is determined in the whole study. This

measure will help the Urban Community in the analysis of the different variables and factors
present in the study and how these connect to each other.
TASK 2.3
Present further outcomes, for supporting the decisions made under above task
With the help of the decision made in the above discussion, the regression analysis model
of the machine learning can be used for data analysis. The regression creates a relationship
among the different variables of the data set. The business in the case can use it to the forecasting
of the sales and risks which can be there in the market. It helps in the determination of the
dependent and the independent variable in the study. For example, the company may use this
tool for the prediction of the numbers of goods which have been purchased by the customers and
the demand of the same in the market (Hong and et.al., 2020). The demand and the purchase of
the goods are not the same in this scenario. The regression analysis checks the impact of the
independent variable which mainly determines the level of revenue of the business. The Urban
Community will be helped with this forecasting as it will aid them in optimising the different
processes of the business in a way which would maximise the profits and the growth of the
business in a short period of time. The tool will help the business to take the decisions in the
business more optimally and highlights the main area where the business needs to put the main
focus to guarantee an efficient use of its resources. The business managers do not have to form
judgements based on their own and can use more authentic and correct decisions after a detailed
interpretation of the market and the variables which influence the working of the business. The
management can now work using a scientific angle. The raw data can be considered as an
actionable plan and knowledge. With the help of this, smart choices can be made in the
organisation.
The business can achieve a better insight in the understanding of the other patterns which may
influence the sales and the profits of the business. The regression analysis helps in understanding
the different patters which may arise in the data set which are valuable for a business to take into
consideration (Hossain and et.al., 2020).
The business achieves the optimization of the processes of the business and helps in
maximization of the efficiency of the business processes with the help of the statistical data.

The use of this tool eliminates the errors and the issues which may arise while having a
critical analysis and the judgements of the strategic managers of the organisation. The business
can achieve in prevention of any kind of mistakes which may arise in the absence of the
managers.
TASK 2.4
Give recommendation on the implementation, acceptance and assessment of the decision along
with discussing that how it contributes to strategic management.
There are many advantages for the organisation which makes better use of regression analysis.
The decisions may be adopted by the business to further advance the growth and the profits of
the business. The Urban community will take use of regression analysis in management of the
different tasks in the business and does not consider any assumptions in the working. The
different confusions that may arise in the business can also be eliminated in the business and the
estimates may be provided with the help of the data calculated and collected. The business is
required to focus on the efficient ways of using these tools and need to employee more
technologically advanced employees which will make better use of the software like SPSS and
Excel. The major requirement would be of someone who knows about machine learning and
business should acquire someone with that skillset and knowledge.

REFERENCES
Books and Journals
Egger, R., 2022. Topic Modelling. In Applied Data Science in Tourism (pp. 375-403). Springer,
Cham.
Silveira and et.al., 2021. Modelling aboveground biomass in forest remnants of the Brazilian
Atlantic Forest using remote sensing, environmental and terrain-related data. Geocarto
International. 36(3). pp.281-298.
Raikov, A., 2020. Megapolis tourism development strategic planning with cognitive modelling
support. In Fourth International Congress on Information and Communication
Technology (pp. 147-155). Springer, Singapore.
Balasubramani, D.P. and Dodagoudar, G.R., 2022. Modelling the spatial variability of Standard
Penetration Test data for Chennai City using kriging and product-sum
model. Geomechanics and Geoengineering. 17(1). pp.92-105.
Franks, P.J., 2018. Recent advances in modelling of harmful algal blooms. Global ecology and
oceanography of harmful algal blooms, pp.359-377.
Jiang and et.al., 2019. Dynamic modelling of customer preferences for product design using
DENFIS and opinion mining. Advanced Engineering Informatics. 42. p.100969.
Hossain and et.al., 2020. Reconceptualizing integration quality dynamics for omnichannel
marketing. Industrial Marketing Management. 87. pp.225-241.
Abbasian and et.al., 2018. Improving early OSV design robustness by applying ‘Multivariate Big
Data Analytics’ on a ship's life cycle. Journal of Industrial Information Integration. 10.
pp.29-38.
Henares and et.al., 2019. Quantitative integration of sedimentological core descriptions and
petrophysical data using high-resolution XRF core scans. Marine and Petroleum
Geology. 110. pp.450-462.
Jadhav, M.R.D. and Kadam, D.M.S., 2020. Incubated insights: Data Integration. Reliability for
Effective and Efficient Pharmacy shops Business, Our Heritage Journal, and Impact
factor 4.912, ISSN: 0474, 9030.
Potapov and et.al., 2021. Mapping global forest canopy height through integration of GEDI and
Landsat data. Remote Sensing of Environment. 253. p.112165.
Büttner and et.al., 2019. A test metric for assessing single-cell RNA-seq batch correction. Nature
methods. 16(1). pp.43-49.
Madhavrao, R. and Moosakhanian, A., 2018, September. Integration of digital weather and air
traffic data for NextGen. In 2018 IEEE/AIAA 37th Digital Avionics Systems
Conference (DASC) (pp. 1-8). IEEE.
Fedushko, S. and Ustyianovych, T., 2019, January. Predicting pupil’s successfulness factors
using machine learning algorithms and mathematical modelling methods.
In International Conference on Computer Science, Engineering and Education
Applications (pp. 625-636). Springer, Cham.
Hong and et.al., 2020. Improved PM2. 5 predictions of WRF-Chem via the integration of
Himawari-8 satellite data and ground observations. Environmental Pollution. 263.
p.114451.