qwertyuiopasdfghjklzxcvbnmqwertyuiop

asdfghjklzxcvbnmqwertyuiopasdfghjklzxc
vbnmqwertyuiopasdfghjklzxcvbnmqwerty
uiopasdfghjklzxcvbnmqwertyuiopasdfghj
klzxcvbnmqwertyuiopasdfghjklzxcvbnmq
Data Analytics

wertyuiopasdfghjklzxcvbnmqwertyuiopas
Disruptive Technology Innovation

dfghjklzxcvbnmqwertyuiopasdfghjklzxcv
Mr. Arindam Ghosh

bnmqwertyuiopasdfghjklzxcvbnmqwertyu
iopasdfghjklzxcvbnmqwertyuiopasdfghjkl
zxcvbnmqwertyuiopasdfghjklzxcvbnmqw
ertyuiopasdfghjklzxcvbnmqwertyuiopasd
fghjklzxcvbnmqwertyuiopasdfghjklzxcvbn
mqwertyuiopasdfghjklzxcvbnmrtyuiopasd
fghjklzxcvbnmqwertyuiopasdfghjklzxcvbn
mqwertyuiopasdfghjklzxcvbnmqwertyuio
pasdfghjklzxcvbnmqwertyuiopasdfghjklz
xcvbnmqwertyuiopasdfghjklzxcvbnmqwe
rtyuiopasdfghjklzxcvbnmqwertyuiopasdf
Overview of Data Analytics

Data Analytics refers to the process of examining large datasets to uncover hidden patterns,
correlations, trends, and insights that can be used to make informed decisions. It combines tools,
techniques, and algorithms to analyze raw data, transforming it into actionable information. The
primary goal is to support better decision-making by identifying valuable insights that can
improve efficiency, productivity, and innovation.

Importance of Data Analytics

 Informed Decision-Making: Data analytics enables organizations to base decisions on

data-driven insights, leading to more accurate and reliable outcomes.
 Competitive Advantage: Companies that use analytics effectively can outperform
competitors by understanding market trends, customer behavior, and operational
inefficiencies.
 Efficiency and Optimization: It helps streamline operations by identifying areas of
waste or inefficiency, allowing for better resource allocation.
 Predictive Insights: Predictive analytics helps forecast future trends and behaviors,
assisting in strategic planning and risk management.

Key Types of Data Analytics

1. Descriptive Analytics: Focuses on summarizing historical data to understand what has

happened in the past. This is the most basic form of analytics.
o Example: A sales report summarizing monthly revenue.
2. Diagnostic Analytics: Examines data to understand the reasons behind past outcomes,
exploring patterns and relationships within the data.
o Example: Investigating why a marketing campaign succeeded or failed.
3. Predictive Analytics: Uses statistical models and machine learning algorithms to predict
future trends and events based on historical data.
o Example: Forecasting customer demand for the next quarter.
4. Prescriptive Analytics: Provides recommendations on the best course of action to
achieve desired outcomes, often using optimization techniques and simulations.
o Example: Suggesting optimal pricing strategies to maximize profit.

What is data analytics and types of data analytics?

Data Analytics refers to the process of systematically analyzing raw data to extract valuable
insights, trends, and patterns that inform decision-making. It involves using various tools,
techniques, and methodologies to process large sets of data, enabling organizations to make data-
driven decisions. Data analytics can be applied across industries for optimizing operations,
improving customer experiences, and predicting future trends.

Data Analytics || Disruptive Technology Innovation 2

Types of Data Analytics

There are four primary types of data analytics, each serving a specific purpose in the analysis
process:

1. Descriptive Analytics
o Purpose: To understand and summarize past events or data.
o Function: It focuses on answering the question, "What happened?" by analyzing
historical data to identify trends, patterns, or performance metrics.
o Example: A sales report showing how much revenue was generated last quarter.
2. Diagnostic Analytics
o Purpose: To explain why something happened.
o Function: This type of analysis digs deeper into data to determine the cause of a
specific outcome. It answers the question, "Why did it happen?" by identifying
relationships and correlations within the data.
o Example: Analyzing why a specific product’s sales dropped by examining factors
like seasonality, competitor actions, or changes in customer preferences.
3. Predictive Analytics
o Purpose: To forecast future outcomes based on historical data.
o Function: It uses statistical models, algorithms, and machine learning techniques
to predict what is likely to happen in the future. Predictive analytics answers the
question, "What might happen?"
o Example: Predicting future demand for a product based on past sales trends and
current market conditions.
4. Prescriptive Analytics
o Purpose: To suggest the best course of action for achieving a desired outcome.
o Function: This type of analysis goes beyond predicting future events and
provides recommendations on how to take advantage of potential opportunities or
mitigate risks. It answers the question, "What should we do?"
o Example: Recommending optimal pricing strategies or inventory management
decisions to maximize profit or minimize costs.

Summary of Types of Data Analytics

Type of Question Focus Example

Analytics Answered
Descriptive "What Past data summarization Sales reports, website traffic
Analytics happened?" analysis
Diagnostic "Why did it Exploring causes and Analyzing product
Analytics happen?" correlations performance decline
Predictive "What might Forecasting future Predicting customer churn,
Analytics happen?" outcomes demand forecasting
Prescriptive "What should Recommending actions Optimizing supply chain or
Analytics we do?" or strategies marketing campaigns

Data Analytics || Disruptive Technology Innovation 3

Tools and Techniques of Data Analysis

Data analysis involves various tools and techniques that help transform raw data into meaningful
insights. These tools and techniques are selected based on the complexity of the data, the type of
analysis required, and the objectives of the analysis. Below is an overview of commonly used
tools and techniques.

Tools for Data Analysis

1. Spreadsheet Tools
o Microsoft Excel: A widely-used tool for basic data analysis, offering
functionalities like pivot tables, charts, and built-in statistical formulas.
o Google Sheets: Similar to Excel, with cloud-based collaboration features. It
allows basic data manipulation, formula application, and data visualization.
2. Programming Languages
o Python: A powerful, flexible programming language popular for data
manipulation and analysis. Libraries like Pandas, NumPy, and Matplotlib
simplify data handling, statistical analysis, and visualization.
o R: A language specifically designed for statistical analysis and visualization. It’s
widely used for complex data modeling, predictive analysis, and creating detailed
visual reports.
3. Business Intelligence (BI) Tools
o Tableau: A visualization tool that transforms data into interactive dashboards and
reports. It helps businesses make decisions by presenting insights visually.
o Power BI: A Microsoft tool for creating detailed dashboards and reports. It
integrates well with Excel and other Microsoft tools, making it easy to use for
business analysis.
o QlikView: A business intelligence and data visualization tool used for creating
interactive dashboards and data visualizations for data discovery.
4. Statistical Tools
o SPSS (Statistical Package for the Social Sciences): A tool commonly used for
statistical analysis in social sciences, market research, and healthcare. It provides
functionalities for descriptive statistics, regression, and hypothesis testing.
o SAS (Statistical Analysis System): A comprehensive tool for advanced analytics,
multivariate analysis, and data management, often used in large organizations for
data warehousing and predictive analytics.
5. Big Data Tools
o Apache Hadoop: A framework used to store and process large datasets in
distributed computing environments. It is useful for analyzing massive amounts of
structured and unstructured data.
o Apache Spark: A fast big data processing engine that can handle both batch and
real-time data processing. It’s used for machine learning, data streaming, and
graph analytics.
6. Machine Learning Tools

Data Analytics || Disruptive Technology Innovation 4

 o Scikit-Learn: A Python library that provides simple and efficient tools for data
mining and machine learning. It includes tools for classification, regression,
clustering, and dimensionality reduction.
o TensorFlow: An open-source framework developed by Google for machine
learning and deep learning applications.

Techniques for Data Analysis

1. Data Cleaning
o Purpose: To remove errors, inconsistencies, and missing values from the dataset,
ensuring the data is accurate and ready for analysis.
o Techniques: Handling missing data, removing duplicates, correcting outliers, and
transforming data into a consistent format.
2. Exploratory Data Analysis (EDA)
o Purpose: To summarize the main characteristics of the data using statistical
graphics and visualization methods, allowing the analyst to uncover patterns, spot
anomalies, and formulate hypotheses.
o Techniques: Descriptive statistics (mean, median, standard deviation),
visualizations (histograms, scatter plots), and correlation analysis.
3. Data Visualization
o Purpose: To visually represent data in charts, graphs, and dashboards to help
users understand patterns, relationships, and trends.
o Techniques: Line charts, bar charts, pie charts, scatter plots, heatmaps, and
dashboards for presenting data insights.
4. Statistical Analysis
o Purpose: To apply statistical methods to analyze data, identify relationships, and
test hypotheses.
o Techniques:
 Descriptive statistics (mean, median, mode, standard deviation)
 Inferential statistics (hypothesis testing, regression analysis, ANOVA)
 Correlation and covariance analysis to understand relationships between
variables.
5. Regression Analysis
o Purpose: To determine the relationship between dependent and independent
variables, and to predict future values.
o Techniques:
 Linear regression for continuous outcomes.
 Logistic regression for binary outcomes (e.g., yes/no predictions).
6. Time Series Analysis
o Purpose: To analyze data points collected or recorded at specific time intervals,
helping predict future trends.
o Techniques:
 ARIMA (AutoRegressive Integrated Moving Average) for forecasting.
 Seasonal decomposition for identifying trends, seasonality, and residuals.

Data Analytics || Disruptive Technology Innovation 5

 7. Clustering
o Purpose: To group similar data points into clusters, helping in identifying
patterns and structures in the data.
o Techniques:
 K-means clustering for partitioning data into a set number of clusters.
 Hierarchical clustering for building a tree of clusters.
8. Sentiment Analysis
o Purpose: To analyze textual data to determine the sentiment (positive, negative,
or neutral) expressed within the content.
o Techniques: Natural Language Processing (NLP) and machine learning
algorithms to analyze customer reviews, social media content, or feedback.

Types of Variables in Data Analysis

In data analysis, variables are the characteristics or properties of data that are measured,
observed, or recorded. Understanding the types of variables is crucial because different types of
variables require different methods of analysis. Variables can be broadly classified into two main
categories: Quantitative and Qualitative (or Categorical). Each of these has subtypes,
described below:

1. Quantitative Variables (Numerical / Continues)

Quantitative variables represent measurable quantities and can be expressed as numbers. They
allow for mathematical operations such as addition, subtraction, and averaging.

Types of Quantitative Variables:

 Discrete Variables: These variables take specific, separate values. They are often
countable and have a finite number of possible values.
o Example: Number of students in a class, number of cars in a parking lot, number
of goals scored in a game.
 Continuous Variables: These variables can take an infinite number of values within a
given range. They are measurable and can include decimals or fractions.
o Example: Height of individuals, temperature, time taken to complete a task,
distance traveled.

2. Qualitative Variables (Categorical)

Qualitative variables represent categories or characteristics that cannot be measured but can be
classified or labeled. They describe qualities or attributes.

Types of Qualitative Variables:

 Nominal Variables: These are variables that categorize data without any inherent order
or ranking between the categories. The categories are mutually exclusive.

Data Analytics || Disruptive Technology Innovation 6

 o Example: Gender (male, female), blood type (A, B, AB, O), eye color (blue,
brown, green), brand of car.
 Ordinal Variables: These variables categorize data where the order or rank of the
categories matters, but the difference between the categories cannot be quantified.
o Example: Education level (high school, bachelor's, master's, PhD), customer
satisfaction (poor, average, good, excellent), class rank (first, second, third).

3. Binary Variables

Binary variables are a specific type of categorical variable that can take only two possible values,
typically representing the presence or absence of a particular attribute.

 Example: Yes/No questions, pass/fail status, male/female, on/off.

4. Dependent and Independent Variables

 Independent Variables (Predictors): These are variables that are manipulated or

controlled to observe their effect on dependent variables. They are often referred to as
"predictor" or "explanatory" variables.
o Example: In a study measuring the effect of study hours on exam scores, the
number of study hours is the independent variable.
 Dependent Variables (Response Variables): These variables represent the outcome or
result that is measured or observed in an analysis. They depend on the independent
variables.
o Example: In the same study, exam scores are the dependent variable as they
depend on the study hours.

Data Analytics || Disruptive Technology Innovation 7