Data Analytics
What is Analytics ?
Analytics is the extensive use of data, statistical and quantitative analysis,
exploratory, predictive models, and fact based management to drive
decisions and actions.”
Analytics can be defined as “the analysis of data to draw hidden insights to
aid decision making”.
…… and many more !!!
Frequently used terms
Data Analytics Data Analysis Big Data Data Types
Data Warehouse Data Mining Data Cleansing Data Definition
Data Manipulation Data Transformation Data Wrangling Databases
Data Sources Data Forms Raw and Processed Data
Data Collection Statistics Statistical measures Mathematics
Linear Algebra
Artificial Intelligence Normalization R / Python Hadoop
Text Analytics Algorithms Predictions Patterns
Supervised learning Unsupervised learning Clustering
etc….
Definitions
Statistics is just about the numbers, and quantifying the data. There are many tools for finding relevant
properties of the data but this is pretty close to pure mathematics.
Data Mining is about using statistics as well as other programming methods to find patterns hidden in the
data so that you can explain some phenomenon. Data Mining builds intuition about what is really happening
in some data and is still little more towards math than programming, but uses both.
Machine Learning uses Data Mining techniques and other learning algorithms to build models of what is
happening behind some data so that it can predict future outcomes. Math is the basis for many of the
algorithms, but this is more towards programming.
Artificial Intelligence uses models built by Machine Learning and other ways to reason about the world
and give rise to intelligent behavior whether this is playing a game or driving a robot/car. Artificial
Intelligence has some goal to achieve by predicting how actions will affect the model of the world and
chooses the actions that will best achieve that goal. Very programming based.
Statistics quantifies numbers
Data Mining explains patterns
In short Machine Learning predicts with models
Artificial Intelligence behaves and reasons
https://stats.stackexchange.com/questions/5026/what-is-the-difference-between-data-mining-statistics-machine-learning-and-ai
Types of Analytics
Types of report, analytics
and query Focus
Optimization What’s the best that can happen ?
Prediction What will happen next ?
Analytics
Forecasting What if this trend continues ?
Statistical Analysis Why is this happening ?
Alerts What actions are needed ?
Query and Reports
Drilldown reports Where is the problem ?
Ad-hoc reports How many, how often ?
Standard Reports What happened ?
Data Science
• Art of transforming hypotheses and data into actionable predictions
• For example, we can use models and data to
Predict who will win an election
What products will sell well together (Apriori / Market-Basket analysis)
Who is likely to default on loans
Which advertisements will be clicked on
etc.
• Tools used (but not restricted to)
Empirical Sciences Statistics Business Intelligence Databases Data Warehousing Visualization
Expert Systems Analytics Machine Learning Big Data Data Mining Reporting
• Central goal of Data Science
To deploying effective decision-making models to a production environment
What distinguishes data science itself from the tools and techniques is the central goal of deploying
effective decision-making models to a production environment.
Data Science
These systems share a lot of features:
• Amazon’s product recommendation systems
• Google’s advertisement valuation systems
• Linkedin’s contact recommendation system
• Twitter’s trending topics
• Walmart’s consumer demand projection systems
Built on a large dataset Most of the systems are live or online
Allowed to make mistakes Not concerned with any cause
Machine Learning
• The ability to write a mathematical function that will read an input and produce output
• We provide the function – machine does not pick its own function
• ML considerations
Training data (lots of it)
Model
Cost function (eg: Ordinary Least Squares)
Optimisation (eg: Gradient descent)
Why is learning possible?
Generalisation is possible
eg: if dataset contains travel time between places A and B, function would not generalise if we
predict travel distance between A and C
IID (independent and identical distribution) of data
That’s why gradient descent needn’t go through the entire dataset, since data is similar
… Eventually data will surpass in oil and water in importance
Thank You !!!
