Foundation of Business

Business Analytics
Analytics
What is Business Analytics?

 Managers in business organizations make

numerous decisions every day. Some of
these decisions include;
 What products to make?
 How to price them?
 Where to locate facilities?
 How many people to hire?
 Where to allocate advertising budgets?
 Whether or not to outsource a business
function or make a capital investment?
 How to schedule production?

Public
What is Business Analytics?

 Analytics is – use of data, information

technology, statistics, methods, and
mathematical or computer models to gain
business insight into business operations to
make fact-based decision making
 There are numerous tools like MS Excel, SPSS,
SAS, R-programming, Python, and many other
business intelligence software.
 Business analytics can help improve
management of customer relationships,
financial and marketing activities, human
capital, supply chains, and almost all other
areas.

Public
Examples

 Banks use analytics to predict and prevent credit fraud BANK

 Manufacturers use it for production planning, and control

 Retailers use analytics for product recommendation and promotion optimization
 Pharmaceutical firms use it to get life-saving drugs to market quickly
 Leisure industries use analytics to understand sales trends, customer behavior, web
site design, and optimize schedules and bookings.
 Airlines and hotels use it for dynamic pricing and to maximize revenue.
 Sports teams are using business analytics to for game strategy and ticket pricing

Public
Observations

 Market leaders are more likely to be sophisticated in use of analytics.

 Often organizations are overwhelmed with data and struggle to understand how to
use data to improve their businesses

Public
Case study: Mall
You are a mall manager. The sales at the mall is very
low, and the costs are increasing
 What will you do?

Public
Evolution

out with Operations research

 New age business analytics includes
 Data mining, Exploratory Data Analysis
 Simulation and risk analysis
 Statistical Data Analysis
 Operations research
 Visual Data Analysis
 Big-data analysis
 Late 18th century statisticians were  Artificial Learning & Machine Learning
employed by gambling industry in  Natural Language Processing
Europe to analyze games.  Text mining
 Modern analytics started in 1940’s with  Social media analytics
introduction of computers  Dashboard making for KPI monitoring
 In 1958, collection, management,  Forecasting
analysis, and reporting of data was
termed as business intelligence (BI)
 Efficient business practices were carried
Public
Impacts and Challenges

 Companies using analytics report Reduced

costs, Better risk management, Faster
decisions, Better productivity, and Enhanced
bottom-line performance such as Profitability
and Customer satisfaction

Public
Scope of Business Analytics

Business
Analytics

Exploratory Data Prescriptive Data

Analysis Analysis

Predictive Data
Analysis

Public
Type: Exploratory Data Analytics (EDA)

 Exploratory Data Analytics (EDA) is the use of data to understand past and current
business performance and make informed decisions
 EDA can categorize, characterize, consolidate, and classify data to get meaningful
insights into your business.
 Visual Data Analysis (VDA) summarizes data into charts and reports
 Query handling involves drill down into the data and make queries
 EDA answers,
 How much did we sell in each region?
 What was our revenue and profit last quarter?
 How many and what types of complaints did we resolve?
 Which factory has the lowest productivity?
 Descriptive analytics can conduct segmentation

Public
Type: Predictive Data Analytics (PDA)

 PDA can predict the future by examining past data, detecting patterns or
relationships in the data, then extrapolating for prediction,
 A marketer can predict customer response to an ad. campaign
 Stock trader might wish to predict price movements in stock prices
 Winterwear manufacturer might want to predict season’s demand of a specific color and
size
 A bank manager might want to identify the most profitable customers or predict the
chances that a loan applicant will default, or alert a credit-card customer to a potential
fraudulent charge
 Predictive analytics helps to answer questions such as
 What will happen if demand falls by 10% or if supplier prices go up 5%?
 What do we expect to pay for petrol over the next several months?
 What is the risk of losing money in a new business venture?

Public
Type 3: Prescriptive analytics

 Aircraft scheduling, factory layout, and supply chain design involve many
alternatives for decision maker. Prescriptive analytics uses optimization techniques
to find the best alternative to minimize or maximize some objective
 Prescriptive analytics is used in operations, marketing, finance and other areas. For
example,
 To determine the best pricing and ad strategy to maximize revenue
 To the optimal amount of cash to store in ATMs
 To plan the best mix of investments in a retirement portfolio to manage risk
 Other techniques can also be combined with optimization for better decision
making
 Prescriptive analytics addresses questions such as
 How much should we produce to maximize profit?
 What is the best way of shipping goods from our factories to minimize costs?
 Should we change our plans if a natural disaster closes a supplier’s factory: if so, by how
much?

Public
 Analytics on
Spreadsheet

R-programming

Power BI
OR
Tableau
Excel Spreadsheet

 Excel formulas and functions

 Logical functions: IF

Public
Visualising and
Exploring data
Visualising and Exploring

 Dashboards
 Creating charts
 Data queries
 Filter
 Statistics
 Cross tabs
 Pivot table
 Slicers in pivot table

Public
Lab work

 Lab work can be using

 Tableau
 Power BI
 R-programming
 Python
 MS Excel
 ……or any other tool!

Public
Lab work

 Lab work should involve following,  Frequency distribution (Histogram)

 Data Visualization  Percentiles, Quartiles
 Dashboard creation  Cross-tabulation
 Creating pie charts  PivotTables
 Creating bar charts  PivotCharts
 Line charts  Slicers
 Area charts
 Scatter plot
 Bubble chart
 Doughnut chart
 Radar chart
 Geographical data representation
 Tables – Data bars, color scales, Icon sets
 Sparklines
 Data queries, Tables, Sorting, and Filtering,
Sorting
 Pareto Analysis
Public
Descriptive statistical
methods
Descriptive statistical methods

 Population and Sample

 Measures of Location (Central tendency)
 Mean, median, mode
 Measures of Dispersion
 IQR, Variance, SD
 Chebyshev’s theorem
 Measures of Association
 Covariance, Correlation,

Public
Descriptive statistical methods

 Lab work can be using

 R-programming
 MS Excel
 ……or any other tool!

Public
Descriptive statistical methods

 Lab work should involve following,

 Revision of Business Statistics
 Population and Sample
 Measures of Location
 Arithmetic Mean
 Median
 Mode
 Midrange
 Measures of Dispersion
 Range
 Interquartile Range
 Variance
 Standard Deviation
 Skewness
 Kurtosis
 Measures of Association
 Covariance
 Correlation
 Outlier analysis

Public
Public
Big Data

 6 Vs of Big data
 Volume
 Velocity
 Variety
 Veracity
 Value
 Variability

Public
Big Data

 Today, nearly all data is captured digitally. As a result, data have been growing at
an overwhelming rate, being measured by terabytes (1012 bytes), petabytes (1015
bytes), exabytes (1018 bytes), and even by higher-dimensional terms.
 Think of the amount of data stored on Facebook, Twitter, or Amazon servers, or the
amount of data acquired daily from scanning items at a national grocery chain such
as Big Bazaar, Croma.
 Walmart, for instance, has over one million transactions each hour, yielding more
than 2.5 petabytes of data
 This data is called as big data to refer to massive amounts of business data from a
wide variety of sources, much of which is available in real time, and much of which
is uncertain or unpredictable

Public
Big Data

 The volume of data continue to increase; what is considered “big” today will be
even bigger tomorrow. Big data come from many sources, and can be numerical,
textual, and even audio and video data. Big data are captured using sensors, click
streams from the Web, customer transactions, e-mails, tweets and social media,
and other ways
 Big data sets are often unstructured and messy. Not only are big data being
captured in real time, but they must be incorporated into decision making at a
faster rate
 Processes such as fraud detection must be analyzed quickly to have value

Public
Levels of Measurements

Classificatio Natural
Order Distance
n Origin
Nomina No No No
Yes
l
Ordinal Yes Yes No No
Interval Yes Yes Yes No
Ratio Yes Yes Yes Yes

Customer Fortune 500 CX Revenu

name Type rank reported e
Amazon Retail corporation 4 6 250
Apple Consumer Technology 8 7 200
Aramco Petroleum 2 6 200
Exon Mobil Petroleum 7 7 300
Shell Petroleum 9 2 400
State Grid Electric utility 3 6 100
United Health Insurance 10 1 80
Walmart Retail corporation 1 6 300 Public
Probability Distributions
Business Analytics
and Data Modeling
Topics from Business Statistics

 Probability listing
 Theoretical listing
 Empirical listing
 Subjective listing
 Binomial distribution
 Poisson distribution
 Uniform distribution
 Normal distribution
 Exponential
 Discrete Uniform
 Geometric
 Negative Binomial
 Hypergeometric
 Triangular
 Lognormal
 Beta
Public
Sampling and Estimation Business Analytics
Topics

 Sampling Methods
 Sampling Distribution of the Mean
 Statistical testing using t-distribution

Public
Statistical Inference Business Analytics
Topics

 Hypothesis Testing
 One-sample t-test
 Paired sample t-test
 Independent sample t-test
 One-way ANOVA
 Chi-square test

Public