MBAS901
ESSENTIAL ELEMENTS
FOR
BUSINESS ANALYTICS
Yan Qian (yqian@uow.edu.au)
Who Are You?
Who are you?
Where are you from?
What are you interests?
What are you expectations?
What are your experiences with business analytics?
What sparked your interest in BA?
Icebreaker: The Story of Your Name
> story behind your name (meaning/significance)
Question?
UOW email
yqian@uow.edu.au
Consultation times
Forum
Moodle I’ll endeavour to get back Anytime
to you within 24h on a weekday Appointment by email
Resources
Subject Level Moodle Site: Course Level Moodle Site Key text
The slides and notes are continuously updated
Software
Login: https://vle.sas.com/
Assignments
(individual)
A1 A2 A3
Due: in lecture (week 3) Due: 16th March 2024 Due: 19th April 2024
Weighting - 0% Weighting - 50% Weighting - 50%
What is ...?
What is Business Analytics?
Business analytics refers to a broad use of various
quantitative techniques such as statistics, data mining,
optimisation tools, and simulation supported by the query and
reporting mechanism to assist decision makers in making
more informed decisions.
MIN, H. 2016, GLOBAL BUSINESS ANALYTICS MODELS: CONCEPTS AND APPLICATIONS IN
PREDICTIVE, HEALTHCARE, SUPPLY CHAIN, AND FINANCE ANALYTICS
What is Business Analytics?
Methods
& Tools
Business
Analytics
Application People
Domains
Scope of Business Analytics
Descriptive analytics: the use of data to understand past and
current business performance and make informed decisions
Predictive analytics: predict the future by examining historical
data, detecting patterns or relationships in these data, and then
extrapolating these relationships forward in time
Prescriptive analytics: identify the best alternatives to minimise or
maximise some objective
Descriptive Analysis
the use of data to understand past and current business performance and make
informed decisions
these techniques categorise, characterise, consolidate and classify data to convert
them into useful information for the business
Typical questions that DA helps answer: "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?"
Predictive Analysis
predict the future by examining historical data, detecting patterns or relationships
in these data, and then extrapolating these relationships forward in time
these techniques can predict risk and find relationships in data not apparent with
traditional analyses
Typical questions that PA helps answer:
"what will happen if the demand falls by 10% or if supplier prices go up by 5%"
"what do we expect to pay for fuel over the next several months"
"what is the risk of loosing money in a new business venture"
Prescriptive Analysis
uses optimisation to identify the best alternatives to minimise or maximise some
objectives
yields recommendations for next steps
typical questions that PA helps answer:
“What should we do next?”
"How much should we produce to maximise profit?"
"What is the best way of shipping goods from our factories to minimise costs?"
Example
Most department stores clear seasonal inventory by reducing prices
Key question:
When to reduce the price and by how much to maximise the revenue?
Potential applications:
Descriptive analytics: examine historical data for similar products (prices, units sold,
advertising, …)
Predictive analytics: predict sales based on price
Prescriptive analytics: find the best sets of pricing and advertising to maximise sales revenue
BA Focus and Scope
analysing data to understand business performance, identify trends,
patterns, and relationships, and make data-driven decisions to achieve
business goals and objectives
wide range of techniques, methodologies, and tools for analysing data,
including descriptive analytics, predictive analytics, prescriptive analytics,
and data visualisation.
Other Examples
Retail & Healthcare Marketing &
e-commerce Advertising
Sports Analytics Finance
Let’s Discuss
Let's discuss an example of business analytics applied in healthcare:
The specific problem or challenge addressed by data analytics.
The types of data collected and analysed.
The analytics techniques and algorithms used.
The impact or benefits derived from the application of analytics.
Let’s Discuss
Let's discuss an example of business analytics applied in finance:
The specific problem or challenge addressed by data analytics.
The types of data collected and analysed.
The analytics techniques and algorithms used.
The impact or benefits derived from the application of analytics.
Typical Steps:
CRISP-DM Framework
CRoss Industry Standard Process for Data Mining (CRISP-DM)
What is Data Science?
What is Artificial Intelligence?
What is Machine Learning?
Supervised vs Unsupervised
Supervised Learning Unsupervised Learning
Goal: Create a model to predict a target or Goal: Segment data into meaningful clusters;
outcome variable Detect patterns
Tune the model using training data, where No target variable to predict of classify in
target value is known training data
Use the model to predict the target for new
observations Methods: : association rules, clustering
Methods: Classification, Regression
Deep Learning
Deep Learning over ML
GPT Models in Business Analytics
Generative Pre-trained Transformers (GPT)
Use cases:
Predictive Modelling, Natural Language Understanding, etc
AI vs ML vs DL vs ...
-Definition-
AI Refers to the development of systems or algorithms that can perform tasks that would typically require human
intelligence.
ML Subset of AI that involves the development of algorithms and models that can learn from and make predictions or
decisions based on data.
DL Subset of ML that involves neural networks with multiple layers capable of learning representations of data.
GEN AI Subset of DL, refers to AI systems capable of creating content, including images, videos, text, etc., based on input
data.
GPT A specific type of generative AI model developed by OpenAI that uses transformer architecture for natural
language processing and generation tasks.
AI vs ML vs DL vs ...
-Techniques-
AI Natural Language Processing (NLP), Computer Vision, Expert Systems, Robotics.
ML Regression, classification, clustering, dimensionality reduction, neural networks.
DL Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adversarial Networks (GAN).
GEN AI Variational Autoencoders (VAE), GANs, sequence models, reinforcement learning.
GPT Transformer architecture, attention mechanism, large-scale pre-training on text data.
AI vs ML vs DL vs ...
-Scope-
AI
Involves developing systems capable of reasoning, understanding language, recognising patterns, and making
decisions.
ML
Focuses on developing algorithms and models that can learn patterns and make predictions from data without
being explicitly programmed.
DL
Focuses on developing neural networks capable of learning complex representations of data by automatically
discovering features and patterns.
GEN AI Involves the creation of AI systems capable of generating new content that resembles human-created content.
GPT Specifically designed for natural language processing tasks such as text generation, language translation, and text
summarisation.
AI vs ML vs DL vs ...
-Examples-
AI Virtual assistants (e.g., Siri, Alexa), self-driving cars, chatbots, recommendation systems.
ML Predictive models, decision trees, clustering algorithms, neural networks.
DL Image recognition in healthcare, speech recognition in virtual assistants, autonomous vehicles.
GEN AI Creating art, generating realistic images, composing music, text-to-image synthesis.
GPT Text generation, language translation, question answering,..
AI vs ML vs DL vs ...
-Limitations-
AI Limited by the availability of training data, computational resources, and the ability to generalise to unseen
scenarios.
ML Requires labelled data for supervised learning, susceptible to overfitting, bias, and lack of interpretability.
DL Requires large datasets, significant computational power, and careful tuning of hyperparameters.
GEN AI Limited by the quality and diversity of training data, potential for generating biased or misleading content.
GPT Limited by pre-training data, lack of real-time interaction capabilities, potential for generating nonsensical or
biased text.
Data
Data Sources
Internal: External:
Annual reports Economic trends
Accounting audits Marketing research
Operations management performance Weather data
Human resource measurements etc...
etc...
Database vs Dataset
Database Dataset
a collection of related tables containing a collection of data (often a single
records on people, places, or things. “spread sheet”)
In a database table the columns
correspond to each individual element Examples: Marketing survey responses,
of data (called fields, or attributes), and a table of historical stock prices, and a
the rows represent records of related collection of measurements of
data elements dimensions of a manufactured item
Dataset
variables records
Types of Data
Categorical Data (qualitative data)
Categorical data refers to a data type that can be stored and identified based on the names or labels given
to them.
Types: nominal and ordinal
Numerical Data (quantitative data)
Numerical data refers to the data that is in the form of numbers, and not in any language or descriptive form.
Types: discrete and continuous
Categorical Data
item no nb of games weight eye colour education level
2367 2 62,7 brown High School
0393 10 77,8 brown Bachelor
1836 3 59,4 green High School
2304 5 80,3 blue Master
8904 16 82,5 brown Bachelor
Numerical Data
item no nb of games weight eye colour education level
2367 2 62,7 brown High School
0393 10 77,8 brown Bachelor
1836 3 59,4 green High School
2304 5 80,3 blue Master
8904 16 82,5 brown Bachelor
Introduction to SQL
SQL
Structured query language (SQL)
Programming language for storing and processing
information in a relational database
A relational database stores information in tabular form, with
rows and columns representing different data attributes and
the various relationships between the data values.
Relational Database
https://planetscale.com/blog/schema-design-101-relational-databases
What Can SQL Do?
SELECT execute queries against a database
INSERT INTO insert records in a database
UPDATE update records in a database
DELETE delete records from a database
CREATE TABLE create new tables in a database
etc...
Basic Statistics
Introduction to Statistics
Find the mean, median, mode, and range of the following data set:
Sort the numbers:
Descriptive Statistics
Mean:
Mode = value that appears most frequently in a data set:
Range = difference between the highest and lowest values:
Median = middle value in a set of data:
Introduction to Statistics
Find the mean, median, mode, and range of the following data set:
Sort the numbers:
Descriptive Statistics
Mean:
Mode = value that appears most frequently in a data set:
Range = difference between the highest and lowest values:
Median = middle value in a set of data:
Descriptive Statistics
Mean:
Mode: > bimodal dataset
Range:
Median:
Inter Quartile Range (IQR)
median
min Q1 Q2 Q3 max
IQR
Q3 - Q1
Inter Quartile Range (IQR)
Q1 = 5 Q2 Q3 = 13
IQR = Q3 - Q1 = 13 - 5 = 8
Inter Quartile Range (IQR)
Inter Quartile Range (IQR)
Q1 = 9 Q2 = 10 Q3 = 12
IQR = Q3 - Q1 = 12 - 9 = 3
Outlier
Given a dataset, any observation that is outside of the range below, is considered an outlier
Inter Quartile Range (IQR)
Find:
Q1
Q2
Q3
IQR
Outliers
Inter Quartile Range (IQR)
Q1 = 8
Q2 = 13
Q3 = 16
IQR = 16 - 8
Outliers = /
https://vle.sas.com/
Sign in using your username
OR
Create a new profile
