Business Analytics Basics

Definition of Analytics

Analytics is the process of examining data using statistical and computational techniques to derive
actionable insights and support decision-making. It involves data collection, analysis, interpretation,
and presentation. By utilizing analytics, organizations can identify patterns, predict outcomes, and
enhance overall efficiency.

Evolution of Analytics

1. Descriptive Era (1970s-1980s):

o Focused on summarizing past events and presenting historical data.

o Primary tools included spreadsheets and basic statistical software.

o Reports were static and often time-consuming to produce.

2. Predictive Era (1990s-2000s):

o Advanced statistical models and data mining techniques became popular.

o Enabled forecasting of trends and behaviours.

o Industries like finance and retail used predictive analytics for customer
segmentation and risk management.

3. Prescriptive Era (2010s-Present):

o Introduction of optimization algorithms and machine learning.

o Focused on providing actionable recommendations.

o Widely used in logistics, healthcare, and marketing for decision automation.

4. Current Trends:

o Real-time analytics powered by IoT and AI.

o Emphasis on integration of diverse data sources for holistic insights.

o Growing role of augmented analytics to enhance user interactivity.

Need for Analytics

1. Data-Driven Decisions: Helps organizations move from intuition-based decisions to

2. Operational Efficiency: Identifies inefficiencies in processes and suggests improvements.

3. Market Competitiveness: Provides insights into market trends, customer preferences, and
competitor strategies.

4. Risk Mitigation: Predicts potential risks and prepares contingency plans.

5. Customer Understanding: Offers deep insights into customer behaviours, enhancing

Business Analytics vs Business Analysis

 Business Analytics:

o Focuses on leveraging quantitative data.

o Involves statistical and computational methods.

o Supports strategic decision-making.

 Business Analysis:

o Emphasizes understanding business requirements and processes.

o Works on project management and solution delivery.

o Aims to bridge gaps between stakeholders and IT teams.

Business Intelligence vs Data Science

 Business Intelligence (BI):

o Primarily retrospective and diagnostic.

o Focuses on creating reports, dashboards, and visualizations.

o Deals with structured data.

o Tools: Tableau, Power BI, Qlik.

 Data Science:

o Explores unstructured and complex data.

o Uses advanced techniques like machine learning, AI, and predictive modelling.

o Seeks to predict outcomes and automate decisions.

o Tools: Python, R, TensorFlow.

Data Analyst vs Business Analyst

 Data Analyst:

o Focuses on processing and interpreting data.

o Responsibilities include data cleaning, visualization, and trend analysis.

o Works closely with datasets to deliver actionable insights.

 Business Analyst:

o Concentrates on understanding business challenges and proposing solutions.

o Collaborates with stakeholders to document requirements and evaluate solutions.

o Ensures successful implementation of projects.

1. Descriptive Analytics:

o Answers: "What happened?"

o Tools: Dashboards, summary reports.

o Example: Monthly sales figures.

2. Diagnostic Analytics:

o Answers: "Why did it happen?"

o Tools: Statistical analysis, root cause analysis.

o Example: Identifying reasons for a decline in customer retention.

3. Predictive Analytics:

o Answers: "What is likely to happen?"

o Tools: Regression analysis, machine learning.

o Example: Forecasting product demand.

4. Prescriptive Analytics:

o Answers: "What should we do?"

o Tools: Optimization algorithms, simulation.

o Example: Recommending the optimal price for a product.

Differences Between Data, Information, and Knowledge

 Data:

o Raw, unorganized facts without context.

o Example: "50, 60, 70" (exam scores).

 Information:

o Processed and organized data with context.

o Example: "The average exam score is 60."

 Knowledge:

o Insights derived from information.

o Example: "Improving teaching methods can increase average scores."

Quality of Data

Key attributes of high-quality data:

1. Accuracy: Ensures data is free from errors and reflects reality.

2. Completeness: Data should be comprehensive without missing values.

4. Timeliness: Data should be current and updated regularly.

5. Validity: Adheres to defined formats and standards for usability.

5Vs of Big Data

1. Volume:

o Represents the sheer scale of data generated daily.

o Example: social media, IoT devices.

2. Velocity:

o Speed at which data is created and processed.

o Example: Real-time stock trading data.

3. Variety:

o Different types of data: structured, semi-structured, and unstructured.

o Example: Text, images, videos, logs.

4. Veracity:

o Reliability and trustworthiness of data.

o Example: Filtering fake news from social media data.

5. Value:

o Focus on deriving actionable insights from data.

o Example: Using customer data to enhance loyalty programs.

Big Data Collection and Ethics

1. Challenges in Collection:

o Handling large-scale, diverse data sources.

o Managing data from real-time systems like IoT.

2. Ethical Considerations:

o Ensuring informed consent before data collection.

o Maintaining transparency on data usage.

o Minimizing algorithmic biases.

3. Regulations:

o Compliance with laws like GDPR (General Data Protection Regulation) and HIPAA
(Health Insurance Portability and Accountability Act).
Data Sources and Collection Methods

1. Primary Sources:

o Surveys, interviews, experiments.

o Example: Customer satisfaction surveys.

2. Secondary Sources:

o Databases, published reports, online data.

o Example: Market research reports.

3. Real-Time Sources:

o IoT devices, sensors, website logs.

o Example: Traffic monitoring sensors.

4. Social Media and Web Analytics:

o Platforms like Facebook, Twitter.

o Example: Sentiment analysis of tweets.

Data Privacy, Security, and Ethical Considerations

1. Privacy:

o Protecting personally identifiable information (PII).

o Ensuring anonymity and user consent.

2. Security:

o Implementing encryption, access controls, and regular audits.

o Preventing data breaches and unauthorized access.

3. Ethics:

o Avoiding misuse of data.

o Promoting fairness and minimizing bias in analytics.

Tools for Analytics

1. BI Tools:

o Tableau, Power BI, QlikView: Used for creating interactive dashboards and
visualizations.

2. Statistical Tools:

o R, SAS, SPSS: Ideal for hypothesis testing and data modelling.

3. Data Management Tools:

o SQL, Hadoop, Apache Spark: Used for data storage and processing.
4. Programming Languages:

o Python, Java, Scala: Provide flexibility in building custom analytics solutions.

5. Machine Learning Platforms:

o TensorFlow, Scikit-learn, PyTorch: Enable building predictive models and deep

 Data: Raw, unprocessed facts and figures without context (e.g., "120, 85, 90" could be test
scores).

 Information: Processed data that has meaning and context (e.g., "Student A scored 120 in
Math, 85 in English, and 90 in Science").

 Knowledge: Insights derived from information through experience, analysis, and

2. Quality of Data

Data quality is determined by:

 Accuracy: Free from errors and represents reality.

 Completeness: All necessary data is available.

 Consistency: Data remains uniform across different sources.

 Timeliness: Data is up-to-date.

 Reliability: Data is trusted and credible.

3. 5Vs of Big Data

 Volume: The vast amount of data generated.

 Velocity: The speed at which data is created and processed.

 Variety: Different formats of data (structured, unstructured, semi-structured).

 Veracity: The trustworthiness and reliability of data.

 Value: The usefulness of data for decision-making.

4. Big Data Collection and Ethics

 Collection Methods: Data is collected via IoT devices, web scraping, surveys, transactions,
and social media.

 Ethical Concerns: Issues such as informed consent, bias in data collection, and potential
misuse of personal data.

5. Data Sources and Collection Methods

 Primary Sources: Data collected firsthand through experiments, surveys, or direct

 Secondary Sources: Data obtained from existing sources like research papers, government
databases, and business reports.

 Methods:

o Surveys & Questionnaires

o Interviews
 o Web Scraping

o Social Media & IoT Sensors

o Transactional Databases

6. Data Privacy, Security, and Ethical Considerations in Data Analytics

 Data Privacy: Ensuring user data is collected with consent and not misused (e.g., GDPR,
HIPAA regulations).

 Data Security: Protecting data from breaches using encryption, firewalls, and access
controls.

 Ethical Considerations:

o Transparency in data usage.

o Avoiding biased algorithms.

o Preventing misuse of personal data for unethical purposes.