People  have the notion that Data Science is some what similar to rocket science and they are not the right candidate to take this up.Lets explore the above statement. This is what Wikipedia has to say about Data Science:

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, machine learning, data mining, and predictive analytics,similar to Knowledge Discovery in Databases (KDD).”

Confused ? Well, please let us tell you, Data Science is a buzz word used in the Analytics Industry which basically means the science that goes around data which encompasses the likes of few simple things. Let us note them down and check whether you can relate to them:

  • Identifying the Business Problem(The toughest thing to do)
    • Generally identified by Client or  by Practice Leadership
  • Discovery of  the Data
    • can be shared by Client
    • may be Scraped, crawled,mined or retrieved
    • can be either of Structured.semi-structured or  unstructured
    • Tools that is used in all or either of the above : RDBMS,ETL. NoSQL DB,SQL,Python, R
  • Cleaning the Data
    • SQL,Excel ,SAS, R, Python
  • Exploratory Data Analysis (Check distribution, Charts,Plots & graphs)
    • Measures of Central Tendency, Probability &Common Sense
    • Excel,SAS, R, Python
  • Which one or more methodology to use (Machine Learning and Predictive Modeling Techniques)
    • Linear  Regression
    • Logistic Regression, Classification Algorithms, Decision Trees, Random Forest , Boosting & Bagging, SVM
    • Time Series Forecasting(MA,ARMA,ARIMA,ARIMAX)
    • Clustering and Segmentation (K-NN, Naive Bayes)
    • Deep Learning Methodologies (ANN, RNN, LSTM)
    • Recommendation Engines
    • Search Engines
    • SAS, R , Python, Elastic Search
  • Validate Results
    • K- Fold Validations
    • SAS, R, Python
  • Predict/Advise Probable Solutions
    • SAS, R ,Python & Present in Excel, MS PowerPoint
  • Report Insights
    • Dashboards
    • Excel, Tableau, Qlikview, Spotfire


Well. this more or less covers the the hyped Data Science Practice of the Industry and its flow in chronological order. I know  you might be more confused with the jargon and the acronyms, but we have also a solution to it.

We at UNP have decided to bring Data Science to the masses.We have realized the demand for Data Science and Analytics and its potential. I will give a small example. Have you ever wondered why MBA is so popular ? Why is every one doing MBA ?  The most popular MBA stream is Marketing and Sales and invariably most of the MBA Graduates choose this as there is a constant demand in the market as every product or service needs to be marketed and sold.

Analytics in a way is similar to Marketing where in every Service or Product needs analytics to revamp its features and characteristics and nurture the weak links with constant iterations. This is one of the many supporting analogies which states that like marketing , analytics will have a constant demand in the market as long as there exists Business.

Given this pretext to empower you in Data Science and Analytics we have collated reading materials and videos and blogs and posts regarding some or all of the subdivisions mentioned above, so that our readers get a ONE-STOP-SHOP to all the things they think that they need to go through to  take their 1st step into Data Science.

Stay tuned to UNP for  the part 2 of this Blog where in we will  share some of the materials that we have drawn inspirations from.

Follow Us in Linked in  :

Like our page on Facebook :

Busting the Data Science Hype !

Leave a Reply