Data Analysis and Decision-Making in Automotive Industry Report

This report provides a comprehensive analysis of data analytics within the automotive industry, focusing on its application in decision-making processes. It examines various aspects, including the use of dashboards to visualize data, the current trends in the automotive industry, and the application of data mining techniques. The report also delves into the role of text mining and big data analysis in understanding customer behavior, market trends, and operational efficiency. The analysis covers the CRISP-DM model, cross-value chain analytics, and the strategic objectives of big data analysis, illustrating how companies leverage data to enhance decision-making capabilities, improve customer experience, and optimize business operations. The report also describes the datasets used for analysis, providing a holistic overview of the data science and big data landscape in the automotive sector.

Running head: ANALYTICS FOR DECISION-MAKING
Analytics for Decision-Making
Name of the Student:
Name of the University:
Author’s note:

1
ANALYTICS FOR DECISION-MAKING
Table of Contents
Section A....................................................................................................................................2
Question 1:.................................................................................................................................2
Part a.......................................................................................................................................2
Part b......................................................................................................................................2
Part c.......................................................................................................................................3
Part d......................................................................................................................................3
Question 2:.................................................................................................................................3
Part a.......................................................................................................................................3
Part b......................................................................................................................................5
Question 3..................................................................................................................................6
Part a.......................................................................................................................................6
Part b......................................................................................................................................6
Section B:...................................................................................................................................8
Data Description:.......................................................................................................................8

2
ANALYTICS FOR DECISION-MAKING
Section A
Question 1:
Part a
Singapore is the most compromising city in Asia on the sector of automobiles. Larger
companies of Asia expand their automobile businesses in Singapore. Amongst the different
automobile companies Nissan is one the largest brands in Singapore.
The vision statement of Nissan is “Enriching people’s lives, building trust with our
employees, customers, dealers, partners, shareholders and the world at large.”
The mission statement of the organization “To provide unique and innovative automotive
products and services that deliver superior measureable values to all stakeholders in alliance
with Renault.”
A strategic objective of the organization is “to achieve sustainable, profitable growth.”
Part b
The three charts represent
1. The average amount spent by customers over the six quarters
2. The average amount spent by the customers in different brands
3. The difference in average amount spent and average revenue earned by different brands
Thus, from the three charts, the management can assess the economic performance of the
organization based on the demography, race and marital status of the customers.
From the three charts the management gets an overview of the amount spent by the
customers in the five brands over a range of time. This information can be used by the
management in understanding customer preferences for the different brands. From the charts
we find that the average amount spent by the customers on “Note” is higher than all other
brands of cars. We also find that the average revenue earned is also higher for “Note” which
is essential in having a sustained growth of the vehicle.

3
ANALYTICS FOR DECISION-MAKING
Part c
Filters in the dashboard can narrow down how the amount spent and revenue generated by
the organization is spread across gender, race and marital status of the customers. In the side
panel we find three filters, one each for gender, marital status and race. In each of the filters
there are various parameters. When a particular parameter is selected then the average
amount spent and revenue generated by the requested parameter is shown. For example, let’s
say we want to view the average amount spent and revenue earned during the period for
females. We would unselect the males in the gender filter. The dashboard would change to
reveal the average amount spent and revenue earned for the period for females. With the help
of filters, we can get the data for each segment, which would aid the management in taking
decisions.
Part d
To build the dashboard the title block was used. Next the three sheets were imported.
The first sheet was placed on top. The second and third sheet were placed below. The filters
were imported from the sheet. The filters were assigned as global filters. Assigning the filters
to be global enabled the use filtering to be shown on all the charts simultaneously.
Question 2:
Part a
The current trend of automotive industry is going in the direction of electronics and
software upgradation of automobile industry. Manual testing of automotive parts such as
carputers and Bluetooth technology are being less popular in vehicle technology. As the
outcome of global trend, the automotive industry in Singapore is hampered. It shows the
increment of demand for software and hardware engineering. Purchases and sells of new cars
of Singapore Automobiles provide car financing and exports used cars. They combinedly

4
ANALYTICS FOR DECISION-MAKING
deals with automobile designer, production designer, driver instrumentation designer, quality
engineering, automotive technician along with supplier warranty recovery specialist.
In data mining process, four levels form a framework in which it is probable to
categorize data analysis competence and potential benefits for a company in general. The
Cross-Industry Standard Process for Data Mining (CRISP-DM) involves no optimization or
decision-making. Based on the business understanding, data understanding, data preparation,
modelling and evaluation sub-steps, CRISP tends directly to the disposition of outcomes in
business methods. Automobile industry propose an additional optimization step that
comprises multi-criteria optimization and decision-making support.
Cross value chain analytics is divided in four categories that are:
1. Customer behaviour analytics
2. Market mix analytics
3. Supply chain optimisation analytics
4. Predictive quality analytics
CRISP model deals with huge iterative approach used by data experts to manually
analyse data. The big data analysis reflects the iterations between business understanding and
data understanding. It also controls data preparation and modelling. It evaluates the modelling
interpretation of relevant application experts in evaluation step. The fundamental idea of the
analysis is that the models can be derived from data with the support of flowcharts and
algorithms. This modelling process can run automatically in most of the analytical prospect.

5
ANALYTICS FOR DECISION-MAKING
The data mining approach is depicted from the sensors and integrated into the data
management system. The companies could forecast the models for the system’s relevant
results in terms of quality, variance of process and deviation from target value. Machine
learning options could be utilised within the context for predicting outputs of system.
Part b
Data-mining approach along with semantic network tools demonstrates market
structure, perceptual maps and meaningful insights. A comparison between a market structure
based on user-oriented content data with a market structure achieved from more traditional
sales and survey-based data for establishing authentic differences.
In automobile industry, the production, marketing, sales and retail optimization must
be accessible and helpful for connecting customer. Using software, the analysis of customer
and manufacturer occur in the consecutive process of data analysis, analytical knowledge and
action. Data mining in simulation data is very critical and at best the object of tentative
research approaches at this time.
The automobile industry requires to get learned about the things for which production
organisation interpreted. In this approach, utilization of evolutionary algorithms for
simulation plausible limited to the probable combinations that can be structured. The needed
computing power is available and the inclusion of variables in decreased. The conclusion
eliminates the limitations of analytical data processing, monotonous activities and domain of
decision-making. It helps to forecast such quality errors and utilise optimizing analytics for
decreasing the occurrence. CAD models and simulations typically of technical methods
maintain manufacturing in multi-disciplinary optimization.
However, data mining has its own disadvantages such as privacy, security and misuse
of information. The issue of personal privacy is being enormously increased as the internet is
booming with social cites and e-commerce. Because of the lack of personal privacy security
is also at high risk. Lots of cases regarding hacking of big data of customers is assumed to be
a big problem.

6
ANALYTICS FOR DECISION-MAKING
Question 3.
Part a
Text mining in automotive engineering industry:
Automobile companies work towards the requirement of customers and provide them
with quality services with top priority. They serve car servicing, repair and replacement of
parts, accident claimed insurance and advise to maintain cars to our clients. Another
prominent improvement within the automobile industry is the enhancement about the
concerns of environment that leads to lower carbon emissions. This attempts the boosting of
fuel efficiency by manipulating the weight of vehicles through its materials. Hence,
automotive companies should strike a proper balance between standard safety measures,
compressed energy consumption and responsibility of environment.
The most popular text mining process of extracting necessary and supreme-quality
information is text mining. It is an analysis where data is contained in natural text language.
With the help of it, unstructured textual data through the identification and exploration is
identified. Text mining is also referred as text data mining. Acquiring information from text
is a suggested field of research to the automobile industry.
The text mining procedure targets to advertise technological companies in the platform of
data management, customer retargeting, demand-side platforms and cross-device advertising.
Unstructured data analysis helps statistical modelling and machine learning techniques in text
mining. It could help unorganised data set to be connected with structed data in a database.
An automobile organization can appropriately utilise text analytics for achieving content-
specific values. Text analytics technology is still considered to be an upbringing technology.
Part b
Big data analysis in Automotive engineering industry:
i) Big data objective:
Automobile industry developers and significant stakeholders certainly has become big
game changer. As big data permeating in our day to day lives, there has been prominent
transformation of focus from the typical surrounding to its real value. Big data analysis
provides better understanding, behaviour and preferences of the customers. Automobile
companies stay interested to expand traditional data sets with social media data, browsing
history, text analysis and sensor data for getting a complete picture of the consumers. The
main objective is to establish predictive models.
ii) Big data applications:
Big data analysis has taken a vital role in the branch of engineering that deals with
designing, manufacturing and operating automobiles. Government agencies, businesses,
consumers, data storage providers and data aggregators in Automotive engineering industry
are taking support of big data analysis.

7
ANALYTICS FOR DECISION-MAKING
The companies maintain their target marketing and enhance business operations by taking
inferences from big data analysis. It helps to enhance talent retention and make customer
experience more efficient. In automobile industries, big data analysis helps to detect fraud
and identify individual customer trials too. Overall it can be seen that by applying big data,
operational engineering data, manufacturing organisations can identify faulty equipment and
regulate optimal control parameters. By data mining, the marketing companies build models
based on historical data for estimating the new marketing campaign. With the help of market
basket analysis, an organisation can arrange proper prediction in a way that customer can buy
automobile products.
iii) Big data analysis helps to achieve the strategic objectives:
Many objectives of big data analysis use the new tools required a term that distinguish the
previous technologies. It is the best possible way to analyse huge amount of organisational
data for managing critically. Strategically, big data companies extend their foot by enhancing
decision-making capabilities. It suggests to gain an edge over their competition. Automobile
industries continuously seek experts with a big data certification for the prosperity of their
company. The analysts are likely to have the efficiency and the expertise for analysing huge
datasets.
The strategic focus of an automobile company is to maintain problem solvers that study
large data streams and establish automated systems for recovering data. The companies
maintain their businesses usually to have data in various forms of market research, logistics,
sales figures and communication costs. A data analyst uses the big data and creates insights
for enhancing decision-making. Database management manages the database of company and
sort out day to day issues. A database administrator understands the latest technologies and
criterion.
In a company, a data scientist should be business oriented with the skills to conduct
effective data evaluations. They should also be capable to make recommendations about
increasing trends and advise companies on the needed actions. As per strategy:
 Companies should ensure the database tools and services remain active throughout
their use.
 Project managers of automobile companies must monitor data compilation and make
sure that it happens accordingly with legal regulations.

8
ANALYTICS FOR DECISION-MAKING
 A particular automobile industry should make sure that the data remains backed-up
safely.
 The automobile organisations should check the data entry methods and help to build
new databases.
Section B:
Data Description:
The data set consists 9 variables. These are CustID, Age, Gender, MaritalStatus, Race,
Date, Amount, Product and Revenue. The age, Amount, Product and Revenue are numerical
variables whereas others are categorical variables.

9
ANALYTICS FOR DECISION-MAKING
Bibliography:
What is text mining (text analytics)? - Definition from WhatIs.com.
(2018). SearchBusinessAnalytics. Retrieved 10 March 2018, from
http://searchbusinessanalytics.techtarget.com/definition/text-mining
Hofmann, M., Neukart, F. and Bäck, T., (2017). Artificial Intelligence and Data Science in
the Automotive Industry. arXiv preprint arXiv:1709.01989.
Career Opportunities Available through Big Data and Data Science Courses. (2018). Big
Data Hadoop Pro. Retrieved 10 March 2018, from
http://bigdatahadooppro.com/career-opportunities-available-through-big-data-and-
data-science-courses/
What-are-the-objectives-of-big-data. (2018). https://www.quora.com/. Retrieved 10 March
2018, from https://www.quora.com/What-are-the-objectives-of-big-data
Ferreira, João. (2018). KNOWLEDGE MANAGEMENT IN AUTOMOBILE
INDUSTRY. www.researchgate.net. Retrieved 10 March 2018, from
https://www.researchgate.net/publication/238067378_KNOWLEDGE_MANAGEME
NT_IN_AUTOMOBILE_INDUSTRY
Mine Your Own Business: Market-Structure Surveillance Through Text Mining | Marketing
Science. (2018). Pubsonline.informs.org. Retrieved 10 March 2018, from
https://pubsonline.informs.org/doi/abs/10.1287/mksc.1120.0713
Huang, L., & Murphey, Y. (2018). Text Mining with Application to Engineering
Diagnostics. Text Mining with Application to Engineering Diagnostics. Retrieved 10
March 2018, from http://Text Mining with Application to Engineering Diagnostics
Advantages and Disadvantages of Data Mining. (2018). ZenTut. Retrieved 10 March 2018,
from http://www.zentut.com/data-mining/advantages-and-disadvantages-of-data-
mining/
Deloitte. (2018). Www2.deloitte.com. Retrieved 10 March 2018, from
https://www2.deloitte.com/content/dam/Deloitte/uk/Documents/manufacturing/
deloitte-uk-automotive-analytics.pdf
Rajpathak, D. (2018). An ontology based text mining system for knowledge discovery from
the diagnosis data in the automotive domain. Retrieved 10 March 2018, from
https://www.sciencedirect.com/science/article/pii/S0166361513000456