Data Science. Business Analytics is the statistical study of business data to gain insights. Data science is the study of data using statistics, algorithms and technology. Uses mostly structured data. Uses both structured and unstructured data.
2. How do you define Business Analytics?
Business analytics (BA) is the practice of iterative, methodical exploration of an
organization’s data with emphasis on statistical analysis. Business analytics is used by
companies committed to data-driven decision making.
Business Analytics is used to gain insights that inform business decisions and can be
used to automate and optimize business processes. Data-driven companies treat their
data as a corporate asset and leverage it for competitive advantage. Successful business
analytics depends on data quality, skilled analysts who understand the technologies and the
business and an organizational commitment to data-driven decision making.
3. What does a Business Analyst do?
A business analyst's daily job duties can vary greatly, depending on the nature of the current
organization and project. However, there are some activities that the business analyst will
commonly do in the course of every project.
They include:
1. investigating goals and issues.
2. analysing information.
3. communicating with a wide variety of people.
4. documenting findings.
5. evaluating solutions.
4. Investigating: Business analysts spend a good deal of time asking questions. Regardless of the project
domain, there are some questions every BA should ask.
Analyzing: Business analysts spend a great deal of time analysing the information they acquire—studying
it for patterns and trends; continually reviewing it to ensure that it is current, thorough, and accurate; and
probing deeply for the sources of a problem and potential solutions. Tools like Root Cause Analysis, Gap
Analysis, and Business Process Modelling can help here.
Communicating: Good business analysts spend many hours actively communicating. More than simply
talking, this means listening to verbal and non-verbal messages, establishing open dialogue, etc. You can
find a wide variety of resources for this critical skill on our Communications Know-How page.
Documenting: Business analysts spend a fair amount of time documenting what they learn and observe,
and the results of their analyses.
Evaluating: A business analyst must also spend time identifying options for solving specific problems,
then help select the best one.
5. Difference between BI and BA. Yes! They are
different.
Business Intelligence.
What happened?
When?
Who?
How many?
Reporting (KPIs, metrics),
Automated Monitoring/Alerting
(thresholds),
Dashboards,
Scorecards.
Business Analytics.
Why did it happen?
Will it happen again?
What will happen if we change x?
What else does the data tell us that never
thought to ask?
Statistical/Quantitative Analysis,
Data Mining,
Predictive Modeling,
Multivariate Testing.
6. Skills Required by a Business Analyst.
• An interest towards Learning new technologies, New Algorithms and
New methods.
• Strong grasp in Real Analysis, Linear Algebra, Statistics and Basic
Calculus.
• Basic grasp over at least one programming language – Loops,
Control Statements, Data types, Arrays, etc.
• Basic grasp over one statistical software – R, Python, MATLAB,
FreeMAT etc.
• Analytical thinking, Ability to ask efficient questions.
• Common Sense, ability to pull down complex concepts to a very
simple concept.
• Detail-oriented with excellent communication and documentation
skills.
7. A small exercise to flex our brain muscles.
How many cigarettes are smoked in India per day?
Instructions: No need to give me an exact answer, because there are parameters
affecting your decisions which we are not aware of.
I need an approximate, logical and digestable estimate. This is called
Guesstimates.
One of the most favourite topics used to test the analytical skills of a person
applying for a Business Analyst position.
8. Resources :
• Smart BA (http://smart-ba.com) : They teach you business analysis by applying
the concepts of BA in solving a Business Analyst Murder Mystery!!.
• Bridging the Gap (http://www.bridging-the-gap.com/) : Laura Brandenburg,
holds a 8 lesson course for budding business analysts. (Google her!).
• Competitive Strategy by Ludwig-Maximilians-Universität München (LMU), by
Coursera.
• Learn the art of Effective Problem-Solving and Decision-Making, a course
offering from UCI aimed at helping learners develop critical thinking skills.
9. Introduction to Data Science.
Definition:
Data Science is an interdisciplinary field about processes and systems
to extract knowledge or insights from data in various forms, either structured or
unstructured, which is a continuation of some of the data analysis fields such
as statistics, data mining, and predictive analytics, similar to Knowledge Discovery
in Database (KDD).
Imagine: You have a machine that can answer any question. However, you can
only ask it one question. What will you ask it?
10. Data Scientist? What do they do?
• Collect Data.
• Clean data.
• Explore data.
• Discover Patterns.
• Analyse the System/Market.
• Design Model.
• Prediction and Decision.
11. Why data science at all?
• In the last decade, the amount of data in the world has increased
exponentially.
• Are we drowning in data?
• There are companies like Google, Facebook and others who are making use of
this data to enhance their User Experience.
• Integrate data effectively(Data Mining); Don’t look at everything, see for only
what you want (Feature Extraction); Store the data effectively (Data
Warehousing).
12. What does it take to be a data scientist?
• MATHEMATICS :
1. Statistics – Distributions, Expectation, Measures etc.
2. Probability – Likelihood, Density Functions, Baye’s Theorem etc.
3. Linear Algebra – Vector Spaces, Vectors, LU, SVD, Moore-Penrose…
4. Matrix theory – High School Level.
5. Calculus – High School Level.
• PROGRAMMING :
1. C/C++/Python/Java.
2. R/SAAS/Python/MATLAB.
• BUSINESS APTITUDE:
1. Market Dynamics.
2. An eye for detail.
• OTHERS: Hard work, Avid Reader attitude, Learn something new every minute.
13. Commonly tools used:
• Python :
There are various packages used in Python for Data Science. There is Numpy,
Matplotlib, Pandas, Seaborn, Sklearn and thousands of other ones. Don’t believe
me? Go here: Installing all of them individually is a time taking and difficult,
specially if you are on windows (Pip!!).
14. To make our life simpler,
We have WinPython (both in 2.x and 3.x).
[The installers are available with me, interested people may take it].
We have Anaconda.
I prefer WinPython, because it is Local and Portable. Meaning, it won’t mess with
my System configuration.
15. • R
R is a statistical software. Similar to Python, R also has a million packages, plyr,
dplyr, ggplot, ggplot2, zoo, ts etc.
Again, similar to PyPi, we use CRAN for R packages.
Some basic disadvantages of R : You need to have the internet even when you
are installing the packages locally (Something I discovered on my own during
verifying Zipf’s Law).
What I did is, I will just share my mobile hotspot on my laptop and install the
package (Got me 10 points on SO).
16. I always found installing Packages locally.
Steps : Find Package -> Download the <package name>-release.zip file -> Run
Rstudio -> Go to tools -> Install Packages -> Install From -> Package Archive File
-> Browse -> Find your file and hit INSTALL.
Also, R packages have a long range of Dependencies, so, its kind of interesting
and if you read the package documentation, they are great dumps of
knowledge.
As far as the installation is concerned, you need to have the bare backbone R,
followed by Rstudio. All the technicalities are taken care of by Rstudio.
19. Resources:
• Coursera – Intro to Data Science.
• Udacity – Intro to Data Visualisation using d3.js.
• NPTEL – Intro to Data Analytics.
• KdNuggets, Analytics India, Data Science Central etc.
• Please read research papers on a semi-regular basis.
• And many many more.