Data Handling and Business Intelligence

Data handling and
Business Intelligence

Contents
PART 1............................................................................................................................................3
1. Use of excel of pre-processing the data:.............................................................................3
1.1.1 Use of IF function in Excel:..........................................................................................5
1.1.2 VLookup:.......................................................................................................................5
1.1.3 Charts and Graphs:........................................................................................................6
PART 2............................................................................................................................................8
2.1 Using the audidealership.csv provided in conjunction with Weka give a specific example
of clustering............................................................................................................................8
2.2 Most common data mining methods which are used in business with real world examples.
................................................................................................................................................9
2.3 Advantages and disadvantages of Weka over excel.......................................................12
REEFRENCES..............................................................................................................................14

INTRODUCTION
In present time, businesses have large amount of data related to different operating
activities which is needed to be controlled and effectively managed to make useful results. Data
handling is a modern technique which support in managing and assorting of large data into
presentable group which make easy analysing and summarizing of key findings. In this report,
large data related to superstore of car is used to identify and critically evaluate the current trends
in data warehousing, business intelligence and data mining. In addition report also demonstrates
a comprehensive knowledge and systematic understanding of essential concepts and principles
by using predictive analytic software.
PART 1
1. Use of excel of pre-processing the data:
Prior to quantitative analysis, the data pre-processing comprises of a variety of measures
for converting raw database from data acquisition into a ‘safe’ and ‘tidy’ dataset. Data pre-
processing is a tool for the data mining which transforms raw data into a comprehensible format
(Pashazadeh and Navimipour, 2018).
The data are also presented in line graphs, diagrams and histograms. In Excel, we will play
with other kinds of information from different data facets. From production to small shops and
government agencies MS Excel is hardly used.
Individuals in every office realize what the key significance of the expression for this most
common program is:
1) Pivot Tables
PivotTables collects vast volumes of Excel data using a structured table where heading
for first row and Definitions or Attributes for the second row are used. The description of data is
versatile, but typically Pivot table values for some or all categories are included. Excel 2013 will
evaluate the data and propose Pivot Table for if is new to building Pivot Table. Tap on each
of cells either table in range:
How this function is working: In Pivot Table Suggested dialogue box, select one that
operates best and click OK every Pivot Table design. Excel can provide the data with a set of
suggested pivot tables. Excel after which positions, Pivot Table on new worksheet as well as
displays field list to reorganize the information to fit requirements.

2) Conditional Formatting
As name suggests, conditional layout adjusts the cell structure based on cell material, or
some cell or cells in workbook or some other. Conditional layout lets users easily concentrate on
main elements of a table or show mistakes and recognise relevant data trends.
The specified conditional formats are used for cell depending on the location one set or
on location generated by Excel by contrasting cell variables in range. For e.g., with any
compensation above a certain sum, any employee before a certain date or any individual with a
certain name, the status quo may be extended in a list of employees' salaries. The manager
enters. The salary column will have graphical conditional templates and the largest and lowest
amounts in the table will be evaluated by choice, but can also be overridden where possible.
3) Sorting and Filtering
Excel tablets help us to understand large quantities of data. You may order the details or simply
pick the data that you need, depending on the parameters you defined in MS Excel, to render it
easy to locate what you want. Order and sort the data saves time and increases the productivity of
your chart. Guess one had a list of 100 records, the dates, ages, different names, towns, and much
more. With Excel's sort and filter functionality, you can easily organize data as per user needs
(Patan and Babu, 2018).
4) Basic Math
The biggest challenges are numbers of every Excel row. One aspect that makes Excel so
efficient is the use of simple math functions which control such numbers. In Excel's formula bar,
simple measurement as it will be written down could be entered. Start the computation using the
= symbol, like all Excel equations. When one click Enter, the result emerges inside the cell or
shape bar. The equation should be placed straight onto cell or formula bar. A further option, as
can be found here (in which cell A1 (or 87) + cell A2 (or 16) is equitable to cell A3 (or 103)), is
to make multiple type cells.
5) Mixed Type Charts
The hybrid or mixed form charts blend two types of charts, including the Excel chart for the
column and the line chart for example. This layout can assist exhibit two distinct information
kinds or a wide variety of values. For instance, the no. of homes being sold during Jun to Dec.
and average monthly selling prices can be identified more easily using a line graph (Young-
Saver, and et.al., 2018).