Data Handling and Business Intelligence

Data handling and business
intelligence

Contents
INTRODUCTION...........................................................................................................................1
PART 1............................................................................................................................................1
Evaluating the use of Excel for pre-processing, analysing and visualising the data using
Superstore data and determining the decline in sales/profits over the years...............................1
PART 2............................................................................................................................................8
2.1 Workings of WEKA using audidealership.csv......................................................................8
2.2 Explaining data mining methods that can be used in business with real world examples. .11
2.3 Discussing the advantages and disadvantages of WEKA over Excel.................................13
CONCLUSION..............................................................................................................................14
REFERENCES..............................................................................................................................15

INTRODUCTION
Data handling is a procedure of recording, analysing, interpreting and evaluating the data
set. The concept of data handling is related with business intelligence which helps in utilising
the tools of data handling in operations of a business organisation (Bordeleau, Mosconi and
Santa-Eulalia, 2018). The main aim of this report is to build an understanding about how data
systems work and how their benefits can be optimised. This report is divided into two sections.
In first section of this report, current trends in data warehousing, business intelligence and data
mining are discussed. Along with which, a data set of superstore is used in order to practically
use the Microsoft Excel functions. These functions will be used to determine the decline in sales
and profit of superstore.
In the second section of this report, data of audidealership is used for clustering the data
using an analytic application of WEKA. In this section, various data mining methods are also
analysed along with their associated real life examples. Finally advantages and disadvantages of
WEKA application are discussed over Microsoft Excel.
PART 1
Evaluating the use of Excel for pre-processing, analysing and visualising the data using
Superstore data and determining the decline in sales/profits over the years
Data warehousing is the practice of storing the data so that it can be used whenever it is
required. This concept is used by various business organisations to store and organise their
business information so that it can protected. The current trends for data warehousing in market
are optimisation and performance by creating a balance between disk storage and memory.
Another trend in this field is In-memory database management system. This trend is result of
bridging the issue of slow query response system (Mitrovic, 2020).
Business intelligence is a system which allows its users to use tools and techniques by
which simple data can provide meaningful insights and information which can be used for
business operations. Current trends for business intelligence in market are open source BI and
software as a service. By using open source BI, small scale organisations can use tools of BI
without any license acquisition and free of costs. On the other hand, SaaS is the result of
increasing demand of software for forecasting and predictions.
1

Data mining is the procedure of mining the pre stored data by running algorithms and other
functions to mine the additional information from the data which is not visible by only looking at
the data set. The current trends which are observed in the field of data mining are Visualisation
and service oriented architecture (Fuchs, Höpken and Lexhagen, 2014). Visualisation is the trend
which is being highly used by business organisation as it allows presenting the mined
information by using graphs, charts and tables. On the other hand, service oriented architecture
helps in mining only that data which can result in providing useful insights to the company.
There are various software applications which are used to conduct above procedures of data
warehousing, business intelligence and data mining. One of those applications is Microsoft
Excel, using this application; its usage for pre processing, analysing and virtualising the data is
evaluated.
Pre processing the data
The data in superstore dataset is raw and is required to be pre processed before analysing.
Excel is analytic software which has various options to pre process the data. Among all those
tools and functions, the function of identification of missing values, PIVOT table, FILTER and
SORT are used. By using the shortcut key of Shift + F4, all the missing values (product base
margin) in dataset are identified and then filled by their mean values. Once the dataset is
cleansed, it is then transformed by using sorting and filters option so that all values can be shown
according to their order date. Lastly, the dataset is reduced to only few values using PIVOT
table. The selection of these variables is done on the discretion that only those variables will be
selected which can impact organisation’s profit and sales.
Analysing the visualisation
Once the dataset is processed, it is then essential to analyse and visualise it so that
meaningful insights can be gained. This process of analysis is done using the Excel functions of
SUM(), LOOKUP(), COUNTIF() and CORRELATION. And the process of visualisation is done
by Bar chart and line graph (Ataman, Kulick and Sim, 2011).
First all the numerical values are selected from the PIVOT table and using the function of
sum, total of all numerical values are divided according to four years (2009, 2010, 2011 and
2012). A visual representation of these total values is given in below table. Using the data of the
table, graphs for each variable is also prepared.
2