Data Driven Decisions: Analysis for Bangles Jewellery in the UK Market

This report analyzes data-driven decision-making within Bangles, a UK-based jewellery company. It examines trends shaping the increasing importance of data analysis, including the rise of big data, high expectations for insights, and the use of analytical tools. The report outlines a Problem-Solved Fr...Read More

DATA DRIVEN DECISIONS
FOR BUSINES

TABLE OF CONTENTS
INTRODUCTION...........................................................................................................................1
MAIN BODY...................................................................................................................................1
Trends shaping the increasing importance of Data analysis........................................................1
Analytical approach.....................................................................................................................2
Analysis........................................................................................................................................3
Recommendation and conclusion................................................................................................5
REFERENCES................................................................................................................................7
APPENDIX......................................................................................................................................8

INTRODUCTION
Data driven decisions are the decisions which is made by a business with the help of data
analysis in the business. In this project the company which is selected is Bangles which is a
jewellery company based in UK.
MAIN BODY
Trends shaping the increasing importance of Data analysis
Some trends which were successful in shaping the data analysis increase in companies
like Bangles are,
Big data is everywhere :
In the recent times the generation of data has increased a lot each day. Currently the
generated data in a day is estimated at 2.5 exabytes. For the success of business, the IT of that
company knowns and understand that more the company is successful in extracting data it will
be better for them in the competitive market(Bocca and et.al., 2017). Companies like Bangles
which has the business of jewellery can use the data collected from the market to connect with
customers by providing them offers and deals.
High Expectations :
But the flow of data in the organization ideal leaders have understood that analytics tools
result of the data explosion has been that many businesses and companies have shown great
urgency and excitement for it. Businesses I understood that capturing these data can provide it
new insights for unlocking operational efficiency and business growth. With the help of these
data collection companies like Bangles can influence their decision for investment improvement
or security customer experiences and also increase in productivity.
Analytical tools :
For the flow of data I delete this has understood that harnessing data for the organization
is effective by deploying multiple analytics tool. These tools are there scattered across different
parts of business. For a company like Bangles data is of no use without proper analysis. This is
why these companies use analytic tools for harvesting of data (McKinley and Atkinson, 2020).
Security :
Most of the companies have very high security for the data, however data breaches it is
very common in headlines. This trend increases the data analysis of the company because with
1

the help of these data an organization can increase security with the help of support data driven
communication and collaboration with traditional firewall.
Integration :
The digital transformation of a company is totally dependent on the integration of the
data from multiple application and sources. In an organization data is needed for analytical tools
for data sources, platforms and data management. These challenges which the organization has
to face during the analytics can be solved with the data analysis.
Data value hunting :
The role of a data analytics is to find the valuable insight which can help the business to
improve its business. It is almost a race in the competitors for the valuable data. From the above
trends it is very clear that data is useful for the operation of the Bangles businesses. This
provides the company the reason for data analytics to survive in the competitive market (Molina
and Zeidouni, 2017).
Analytical approach
The approach which can be use for the data analysis is the Problem-Solved Framework.
This process is that process in which problem if not solved it is considered as failure
(Okechukwu, 2020). This approach consists of the following steps,
Business Understanding :
The first step in this process is to understand the business of the company which is using
this approach for data analytics. Bangles is a company that deals with all different kinds of
jewellery both in online and offline market. The problem face by this business is regarding the
performance of its sales in UK market. Thus, in this step the company will plan about making
decisions for solving this problem. It will also gather the information which is required for
making such decisions. For example lets say this company decided to contact with every
customer as its decision thus it will be important for the business to decide which customers in
needed to be contacted.
Data understanding :
In this approach data is said as the raw material which is used for building solutions. The
focus of data understanding is the estimation of cost and benefit each of the data source. Data
understanding can be defined as the process of gathering and analysing data with the help of
logical and analytical reasoning and then applying them to different business problems to solve
2

them. The source of every collected data should be taken into account and the cost benefits
should be examined. The data should help in building a model and all the resources should be
utilised in an optimum way. Different data should be applied to fix different issues and should be
able to prioritize which issues to be resolved first. It also helps in collecting feedback and saving
information from the data to make informed decisions (Ramachandra, 2017).
Data preparation :
It is the process of analysing, evaluating, rectifying, altering and determining the prime
data to be used for business purposes. It helps in ensuring accuracy in the datasets which helps in
making precise decisions. By identifying the process of data preparation, the incompetent,
inessential errors could be reduced and the potential risks and losses could be dodged. By
collecting data according to the goals and objectives of the organization product quality could be
improved, human error can be reduced, return on investment can be increased, data governance
can be enhanced and more data driven information can be produced. The company can take the
help of employees, research providers, can hire consultants or can ask vendors for maintaining a
feedback.
Analysis modelling :
Collecting and analysing the required data and modelling the problem can be effective in
several ways. It is a way of making different data fit together, mapping and visualizing the
information and functions to improve the efficiency. What systems to be used, what type of data
is available and how it can be utilised and the needs of the business should be taken into account.
Keeping in mind these things, a model should be created and how different sources of data will
flow into other source’s (Ramachandra, 2017).
Analysis
Data is known as the facts and information which is collected together with the help of
statistics. Data cleaning is the process which is used for fixing incorrect and corrupted form of
data. It is found incorrect due to incorrect format, duplication, or incomplete data. Combination
of multiple data sources can provide opportunities for data duplication. The steps which are
taken by this company for cleaning incorrect data are,
Remove duplicate and irrelevant observation:
For the process of cleaning data, the most important and easy approach of cleaning is to
remove the unwanted information from the data, including the duplicate observations and the
3

irrelevant observations. The duplication of observations is bound to happen during the time of
data collection. These duplicated observations are to be cleaned in order to make the data
relevant and reliable. The observations which are not applicable and do not fit the analysis, this
type of observations are needed to be removed from the analysis.
Fixing structural errors: Structural errors are the repeated data errors which can be noticed
while transferring file. Duplicate errors, typos can be reduced with the help of data cleaning
tools. These tools analyse the records and cleans the database which makes the datasets more
accurate and easy to use. It is a time saving process as large amount of data can be scrutinized in
less time, which fixes the errors and does not hamper the work of other departments.
Filter unwanted outliers:
Outliers can be very informative and removing them inappropriately can be a difficult
and wrong decision. Outliers are unusual values that can cause problems and misrepresent a
dataset, that’s why it is important to understand why they occurs. It should be removed only for
specific reasons and eliminating it can cause the results to be proportionally significant. The
reason of occurrence of outliers can be measurement errors, typos or mistakes during data entry.
This type of errors is easy to detect and can the values can be rectified. Sampling problems can
also be one of the reason. For example, when data is collected outside the targeted project, which
is not beneficial and might have unusual characteristics. However, the data point can be removed
and a specific reason must be given why it does not represent the target project. In cases of large
sample sizes, there could be natural variations in datasets that can produce outliers but it cannot
be considered incorrect as they could be a part of data distribution.
Handle missing data:
There are different ways of handling missing data’s but few points should be taken into
account. Only those algorithms can be used that support missing data. Some of the observations
that have missing data’s can be neglected but the information it contained should not be lost.
Imputation of missing data on the basis of assumptions can be done but it might reduce the
accuracy of the data as it a proxy for the actual data. Missing values can be replaced by mean,
median and mode values which may prevent data loss and can work well in a small dataset.
4

ANALYSIS
Source : Grand View Research, Inc, 2019
The following illustration shows how the Data analysis of Bangles is used for
understanding the rates of the jewellery and also predicting its prices in the upcoming future.
This is how with the help of data analytics not just the present situation of the business is
understood but it also helps with understanding the future as well. This use of data is very
effective and can be only be done with the help of all the process discussed above (Rebiere and
et.al.,2017).
Recommendation and conclusion
Yes the marketing campaign was a success and had positive on the performance of sales
in the UK. With the help of this project we understand the process of data analysis and how the
analytical process is conducted. The analytical data adds value in companies such as Bangles and
increases the understanding of the problem. The changes in the trends lead to major development
of the data analytical tools and helps much more briefly and accurately. We understand that the
5

cleaning of the data is crucial for conducting the analysis which is done in some steps which are
discussed in the project (She and et.al., 2019).
The data generation has increased aggressively in these past few years which has helped
the companies like Bangles to better understand their customers and work accordingly and
efficiently. The high expectations of data has led it to the footsteps of huge companies and
companies like Bangles which is into jewellery business can interpret the correct understanding
of their investment opportunities. The analysis of everything is successful when some special
analytical tools are applied for the harvesting of data and conducting the data analysis process.
Economic analysis of Bangles describes the laws, statements of tendencies in all the
department of economics which are production, consumption, exchange and the income
distribution. Some important methods of economic analysis are deductive method and inductive
methods. The deductive methods represent an abstract approach towards the data analysis for the
company Bangles. The problem of the premise is to be enquired which lead to a better
understanding of the topic. Hypotheses is an important step in the process of economic analysis
of the company Bangles and the deducting form these hypotheses is the next step to avoid all the
irrelevant and unreasonable types of data and save time for the further process. The economic
analysis of the company Bangles helps the charities and their investors to compare the value of
the result of the social intervention which incur the costs of implementing it. It also helps in
allocating all the resources effectively and efficiently (Zheng and et.al.,2021).
6

REFERENCES
Books and Journals
Bocca, B., and et.al., 2017. Size and metal composition characterization of nano-and
microparticles in tattoo inks by a combination of analytical techniques. Journal of
Analytical Atomic Spectrometry. 32(3). pp.616-628.
McKinley, J.M. and Atkinson, P.M., 2020. A Special Issue on the Importance of Geostatistics in
the Era of Data Science.
Molina, O. and Zeidouni, M., 2017, June. Analytical approach to determine the degree of
interference between multi-fractured horizontal wells. In SPE Europec featured at 79th
EAGE Conference and Exhibition. Society of Petroleum Engineers.
Ramachandra, B., 2017. Development of impurity profiling methods using modern analytical
techniques. Critical reviews in analytical chemistry. 47(1). pp.24-36.
Rebiere, H., and et.al.,2017. Fighting falsified medicines: the analytical approach. Journal of
pharmaceutical and biomedical analysis. 142. pp.286-306.
She, R., and et.al., 2019. Importance of small probability events in big data: Information
measures, applications, and challenges. IEEE Access. 7. pp.100363-100382.
Zheng, Z., and et.al.,2021. Discovery and Contextual Data Cleaning with Ontology Functional
Dependencies. arXiv preprint arXiv:2105.08105.
Online
Grand View Research, Inc, 2019. Industry insights.[Online] Available trough:
<https://www.grandviewresearch.com/industry-analysis/jewelry-market>
Okechukwu, P., 2020. the data analytic approach to business process.[Online] Available trough:
https://medium.com/@okechukwuprincewillw/the-data-analytic-approach-to-business-
problems-9272935d2cec.
7

APPENDIX
The Jewellery market in UK has show some great growth over the years. The market of
Bangles have been effected by this growth in the UK market. This has affected the following
statistics of the Jewellery market share.
Bangles Necklace Earrings Rings Bracelets Others
20.00% 21.12% 5.00% 40.88% 10.00% 3.00%
It is the statistics which shows the sale of different jewellery in UK in 2020. The future
trend of jewellery market in coming years is estimated to reach $480.5 billion in 2025. Despite
have faced issue due to Covid -19.
8

9

10

Notes : Analytical tools :
For the flow of data I delete this has understood that harnessing data for the organization is
effective by deploying multiple analytics tool. These tools are there scattered across different
parts of business
11

Notes :
Integration :
The digital transformation of a company is totally dependent on the integration of the
data from multiple application and sources. In an organization data is needed for analytical tools
for data sources, platforms and data management. These challenges which the organization has
to face during the analytics can be solved with the data analysis.
Data value hunting :
The role of a data analytics is to find the valuable insight which can help the business to
improve its business. It is almost a race in the competitors for the valuable data. From the above
trends it is very clear that data is useful for the operation of the Bangles businesses. This
provides the company the reason for data analytics to survive in the competitive market
12

13

Notes :
Analysis modelling :
Collecting and analysing the required data and modelling the problem can be effective in
several ways. It is a way of making different data fit together, mapping and visualizing the
information and functions to improve the efficiency. What systems to be used, what type of data
is available and how it can be utilised and the needs of the business should be taken into account.
Keeping in mind these things, a model should be created and how different sources of data will
flow into other source’s.
14

15

16

17

18

19