Business Analytics Summary (Units 1.2 - 1.

8)
1.2 Introduction

●​ What is Data Science?

○​ Data Science is a mix of different areas like statistics (maths with data), data
analysis (understanding data), and machine learning (teaching computers to learn
from data).
○​ Its main goal is to get useful ideas and knowledge from a lot of data.
○​ It helps us understand past information and predict what might happen in the future.
●​ Why is it Important for Business?
○​ It helps businesses make better decisions.
○​ It can find hidden patterns in large sets of data.
○​ For example, it's used in banks, hospitals, and online shopping (e-commerce).
○​ It helps with things like predicting sales, optimizing delivery routes, and creating
personalized offers for customers.
●​ What does a Data Scientist do?
○​ A Data Scientist uses skills from machine learning, statistics, and programming (like
using R).
○​ They take raw, unorganized data.
○​ Then, they clean it, find trends, and give clear, useful advice to help businesses.
○​ Their work can improve how a company operates and how customers feel about it.
●​ What will you learn in this lesson?
○​ This lesson will teach you the basics of data and data analysis.
○​ You will learn how analytics are classified and applied in various businesses.
○​ You will also understand what "Big Data" is, its characteristics, and the challenges
that come with it.

1.3 Data and Its Types

●​ What is Data?
○​ Data is like raw information. It's the basic stuff we collect, like numbers, text, or
observations.
○​ Think of it as the ingredients before you cook something.
○​ Data itself has meaning and value, but it's hard to understand until we process it.
●​ Structured vs. Unstructured Data:
○​ Structured Data: This data is organized in a clear way, like in tables, lists, or
spreadsheets. It's easy to work with directly.
■​ Example: An Excel sheet with names and ages in columns.
○​ Unstructured Data: This data is not organized. It's like a messy pile of information.
It needs to be processed first to become useful.
■​ Example: A paragraph of text, or a satellite image.
●​ Why understand Data Types?
○​ Knowing data types helps us choose the right way to analyze data and present
results.
●​ Main Categories of Data:
○​ Data is broadly divided into two main categories: Qualitative and Quantitative.
 ●​ Qualitative (Categorical) Data:
○​ This type describes characteristics or qualities. You can't do math with it easily.
○​ Example: Gender, languages spoken, types of diseases, clothing sizes.
○​ Nominal Data: These are categories with no specific order.
■​ Example: Eye color (blue, brown, green), types of pets. You can count how
many of each, but there's no "higher" or "lower."
○​ Ordinal Data: These are categories that can be ordered logically.
■​ Example: Clothing sizes (Small, Medium, Large). There's a clear order, but
the difference between "Small" and "Medium" might not be the same as
"Medium" and "Large."
●​ Quantitative (Numerical) Data:
○​ This type of data consists of numbers. You can perform calculations with it.
○​ Discrete Data: These are distinct, separate values that can only be counted. They
usually involve whole numbers.
■​ Example: Number of cars, population.
○​ Continuous Data: These represent measurements and can take any value within a
range.
■​ Example: Height, weight, distance.
●​ Data Quality - Important points:
○​ Relevance: Data should be useful and meet the needs of the user.
○​ Accuracy: Data must be true and correct. Inaccurate data is useless for decisions.
○​ Timeliness: Data needs to be available when it's meaningful, like stock information
updating instantly after an order.
○​ Interpretability: Data should be easy to understand. Sometimes, extra information
(metadata) helps explain it.
○​ Coherence: Data should be consistent over time and comparable across different
programs. This helps in tracking changes.
○​ Accessibility: Data should be easy for people to find, get, use, and understand.

1.4 Data Analytics and Data Analysis

●​ What are they?

○​ Data Analytics and Data Analysis are terms often used similarly, but they have
different meanings.
○​ Both help in making decisions based on data.
●​ Data Analytics (The Big Picture):
○​ It's the whole process of looking at large datasets.
○​ The goal is to find trends, patterns, and useful insights.
○​ It uses many techniques to make data meaningful.
○​ Data analytics usually answers questions, solves problems, or predicts future
outcomes.
○​ Types of Data Analytics: There are four main types:
■​ Descriptive Analytics:
■​ Focus: Summarizes past data to describe "what happened."
■​ Example: How well a business performed last year.
■​ Diagnostic Analytics:
■​ Focus: Identifies the causes of trends found in descriptive analytics. It
answers "why did it happen?"
 ■​ Example: Why an Instagram account's subscribers dropped.
■​ Predictive Analytics:
■​ Focus: Uses past data to make predictions about the future. It answers
"what is likely to happen?"
■​ Example: Predicting sales for a new trend in the next six months.
■​ Prescriptive Analytics:
■​ Focus: Suggests actions and outcomes based on analysis. It answers
"what should we do?"
■​ Example: Suggesting ways to improve supply chain management.
●​ Data Analysis (A Specific Task):
○​ It's about inspecting, cleaning, changing, and modeling data.
○​ The aim is to find useful information, draw conclusions, and help in
decision-making.
○​ It usually focuses on answering specific questions from data.
○​ Steps in Data Analysis:
■​ Data Collection: Gathering raw data from different sources.
■​ Data Cleaning: Finding and fixing errors, missing values, or duplicates in raw
data.
■​ Data Exploration: Understanding the data's structure and relationships using
statistics and graphics.
■​ Data Transformation: Changing data into a format suitable for analysis.
■​ Data Modeling: Applying statistical or machine learning models to answer
research questions.
■​ Data Interpretation: Understanding the results and using insights for
decisions or recommendations.
●​ Key Difference Summary:
○​ Data Analytics is a broader field that includes many techniques and processes to
analyze data.
○​ Data Analysis is a part of Data Analytics, focusing on specific tasks like cleaning
and interpreting data.
○​ Analytics finds hidden insights and patterns for business decisions and predictions.
○​ Analysis extracts meaning from data to answer specific questions or solve
problems.
○​ Both are vital for modern decision-making. Analytics gives a full view, while analysis
focuses on practical conclusions.

1.5 Application of Analytics in Business

●​ Why Analytics is Important for Businesses:

○​ Analytics is a key tool for organizations of all sizes and industries.
○​ It helps businesses make smart decisions, improve how they work, and get an
advantage over competitors.
○​ Businesses can understand their past and present, predict future trends, make
operations better, and give customers more personalized experiences.
●​ Key Applications of Analytics in Business:
○​ Understanding Customer Behavior:
■​ Businesses use analytics to understand what customers do and what they
prefer.
 ■​ By analyzing customer data, companies can find trends, guess what
customers will need, and make their products or services more personal.
■​ This leads to happier customers, more sales, and better customer
engagement.
■​ Example: Retailers and e-commerce platforms use it to group customers,
predict their future needs, and tailor marketing campaigns.
○​ Improving Business Processes:
■​ Analytics helps make business operations better.
■​ Analyzing data on inventory, supply chain, and employee performance can
help lower costs and make things more efficient.
■​ Example: Walmart uses predictive analytics to manage its inventory, making
sure the right products are in stores at the right time.
○​ Making Financial Decisions:
■​ Analytics helps companies make smart money decisions.
■​ It can forecast how much money will come in, manage budgets, and check
financial risks.
■​ Example: Banks use predictive analytics to check if a person applying for a
loan will pay it back. They can look at financial history and spending patterns.
○​ Optimizing Marketing Strategies:
■​ Marketing teams use analytics to see how well their campaigns are doing and
understand customer groups.
■​ By analyzing customer data and campaign results, businesses can improve
their marketing to reach the right people and increase sales.
■​ Example: Netflix uses customer viewing data to create original content that
matches user preferences, which keeps customers happy and engaged.
○​ Enhancing Human Resources (HR):
■​ Analytics helps HR improve employee performance, reduce employee
turnover, and make hiring better.
■​ By looking at data on job performance and satisfaction surveys, HR can
make data-based decisions that create a positive workplace.
○​ Efficient Supply Chain Management:
■​ Analytics helps businesses make their supply chains work smoothly.
■​ It can predict demand, manage relationships with suppliers, and minimize
problems.
○​ Developing New Products/Services:
■​ Analytics is crucial for creating new products or services.
■​ By analyzing customer feedback, industry trends, and market conditions,
companies can design products that customers want.
●​ Conclusion:
○​ Analytics is no longer a luxury; it's essential for a successful business.
○​ It gives businesses the tools to make smarter, data-driven decisions, improving their
efficiency, customer service, and profits.
○​ As businesses collect more data, analytics continues to drive innovation and
success.

1.6 Big Data and Its Characteristics

●​ What is Big Data?

 ○​ Imagine a huge sale event, like Black Friday, in a very busy shopping mall.
○​ Thousands of people are buying things, and every purchase creates data: what
they bought, when, and how much they spent.
○​ Now, think about all the malls, stores, and websites globally generating similar data
every second.
○​ This enormous amount of data is called Big Data.
○​ It's data that is too complex, vast, or fast-moving for traditional data processing
methods to handle.
○​ It involves collecting, managing, and analyzing huge amounts of structured,
semi-structured, and unstructured data to find patterns and insights.
○​ Example: When Netflix suggests shows based on your viewing history, it uses Big
Data.
○​ Traditional methods for storing and managing data are inefficient for this amount of
data.
●​ Real-World Examples of Big Data:
○​ Instagram: Many photos and videos are shared every minute.
○​ Twitter: Billions of tweets per year, each with text, images, or audio.
○​ Gmail/Outlook: Billions of emails sent daily with various attachments.
○​ Banks, e-commerce, weather monitoring systems, and CCTVs all contribute to Big
Data.
●​ Characteristics of Big Data (The 5 V's):
○​ Volume: This refers to the huge amount of data generated, often in terabytes,
petabytes, or even exabytes.
■​ Example: Likes, comments, and posts shared by billions of Facebook users
daily.
○​ Velocity: This is the speed at which data is generated, processed, and analyzed.
Real-time processing is often needed.
■​ Example: Stock market systems processing millions of transactions per
second for real-time updates.
○​ Variety: This refers to the different types of data (structured, unstructured,
semi-structured).
■​ Example: Videos from YouTube or tweets have different structures.
○​ Veracity: This is about the accuracy, quality, and trustworthiness of the data. Data
can be messy or incomplete, needing filtering before use.
○​ Value: This means the insights and benefits organizations can get from analyzing
Big Data.
■​ Example: E-commerce companies use data to recommend products,
increasing sales and customer satisfaction.
●​ Big Data vs. Traditional Data (Key Differences):
○​ Data Size: Traditional data is limited (gigabytes to terabytes), while Big Data is vast
(terabytes to petabytes or more).
○​ Data Type: Traditional data is mainly structured (rows, columns). Big Data includes
structured, semi-structured, and unstructured data.
○​ Processing Speed: Traditional data uses batch processing and is slower. Big Data
uses real-time or near-real-time processing.
○​ Storage: Traditional data uses relational databases (like SQL). Big Data uses
distributed systems (like Hadoop, NoSQL).
○​ Complexity: Traditional data is manageable with old tools. Big Data needs
 advanced tools and technologies.
○​ Technology: Traditional data uses tools like MySQL, Oracle. Big Data uses
Hadoop, Spark, NoSQL.
○​ Data Sources: Traditional data has limited sources (e.g., business transactions).
Big Data has multiple sources (e.g., social media, IoT, sensors).
○​ Analysis Focus: Traditional data focuses on historical analysis. Big Data focuses
on predictive, real-time, and trend analysis.
○​ Scalability: Traditional data has limited scalability. Big Data is highly scalable with
distributed systems.
○​ Cost of Analysis: Traditional data can be higher for large datasets. Big Data can
be cost-efficient with modern tools.

1.7 Applications of Big Data

●​ Big Data is used in almost every field now, like banking, healthcare, and entertainment.
●​ Healthcare:
○​ Big Data helps predict health risks and personalize treatments.
○​ Doctors can predict diseases based on a patient's medical history, genetic data,
and lifestyle.
○​ Example: IBM Watson Health uses Big Data to help doctors diagnose and treat
diseases like cancer by processing huge medical datasets.
●​ Retail and E-commerce:
○​ Retailers use Big Data to understand customer behavior and preferences.
○​ This helps them give personalized shopping experiences, increasing customer
satisfaction and sales.
○​ Example: Amazon recommends products based on your past purchases and
browsing history.
●​ Finance and Banking:
○​ Financial institutions use Big Data to detect fraud by watching transaction patterns
and finding unusual activities in real-time.
○​ Example: PayPal uses Big Data algorithms to flag unusual transactions, like
purchases from unfamiliar locations or devices.
●​ Transportation:
○​ Transportation systems use Big Data to analyze traffic, find better routes, and
reduce traffic jams.
○​ Example: Google Maps collects data from GPS and sensors to give real-time traffic
updates and suggest alternative routes.
●​ Media and Entertainment:
○​ Streaming platforms use Big Data to analyze viewing habits and recommend
personalized content.
○​ Example: Netflix studies what shows you watch or skip to suggest similar content,
keeping you engaged.
●​ Education:
○​ Educational platforms use Big Data to track student performance, find learning
gaps, and customize study materials.
○​ Example: Khan Academy analyzes user progress to recommend specific exercises
or videos if a student is struggling.
●​ Manufacturing:
 ○​ Big Data helps manufacturers monitor equipment performance and predict potential
failures.
○​ This reduces downtime and maintenance costs.
○​ Example: General Electric monitors its engines using Big Data to schedule
maintenance before breakdowns.
●​ Government:
○​ Governments use Big Data for urban planning and to optimize resources, making
cities smarter.
○​ Example: Singapore's Smart Nation initiative uses IoT data to manage traffic and
monitor air quality.
●​ Energy and Utilities:
○​ Energy providers use Big Data to analyze consumption patterns, forecast demand,
and improve energy efficiency.
○​ Example: Smart meters collect electricity usage data, helping companies adjust
power distribution and avoid outages.
●​ Social Media:
○​ Social media sites scan user-generated content (posts, comments) to understand
public opinion and trends.
○​ Example: Twitter uses Big Data for sentiment analysis during elections to
understand public opinion about candidates.
●​ Conclusion:
○​ These examples show how Big Data is changing industries by offering new
solutions to complex problems.
○​ Understanding and using Big Data's power is very important today.

1.8 Challenges in Data Analytics

●​ Data analytics is very powerful, but it also comes with some challenges that organizations
need to overcome to get good results.
●​ Poor Data Quality:
○​ Getting bad quality data, like old or inconsistent data, is a big problem.
○​ Such data can lead to incorrect analysis and wrong decisions.
○​ Example: If a company uses wrong customer details, it might send irrelevant
marketing messages, making customers lose trust.
●​ Data Integration Complexity:
○​ Combining data from many different sources (like databases, IoT devices, social
media) can be very complex.
○​ This is because data often comes in varying formats and structures.
○​ This incompatibility can cause delays and incomplete analysis.
●​ High Resource Needs (for Big Data):
○​ The huge size of Big Data makes storing, processing, and analyzing it very
demanding on resources.
○​ Handling petabytes of data requires a lot of computing power, which can strain a
company's infrastructure.
●​ Real-time Processing Difficulty:
○​ Getting immediate insights from data (real-time processing) is hard, especially with
very fast-moving data streams.
○​ Delayed insights can lead to missed opportunities in situations where time is critical,
 like fraud detection.
●​ Data Security and Privacy:
○​ Protecting sensitive data from security breaches and making sure rules like GDPR
or HIPAA are followed is very important.
○​ Any data leaks can harm a company's reputation and lead to legal penalties.
●​ Shortage of Skilled Professionals:
○​ There aren't enough qualified data scientists and analysts who know how to use
advanced tools and techniques.
○​ This shortage means organizations might struggle to get useful insights from
complex datasets, slowing down decision-making.
●​ Complexity of Advanced Techniques:
○​ Techniques like machine learning and predictive analytics need advanced
knowledge and powerful computing resources.
○​ Smaller organizations might find it hard to adopt these methods effectively.
●​ Conclusion:
○​ To get all the benefits of data analytics, organizations must overcome these
challenges.
○​ Investing in technology, skilled people, and ethical practices can turn these
obstacles into opportunities for growth.