As we all know that, when the world has entered the era of big data, the question raised was “Where to store this huge amount of data”. It was the concern and big challenge to the enterprise and many other industries until 2010. The only solution to this problem was to build frameworks that can store this data. Then Hadoop and other frameworks came into the picture and so the problem of storing large data was solved. Now the problem was how to process this large amount of data. Data Science is the secret sauce here. 

Therefore it is important to understand what Data Science is and why people are crazy after Data Science. 

Data Science in simple words is the study of data. Data Science is the process through which you can convert raw data into knowledge to support decision making. It involves developing methods of storing and analyzing data effectively. Then through this data, you 

can extract useful information from scientific methods, processes, algorithms, and systems. The main goal of data science is to gain insights and knowledge data that can be both structured and unstructured. 

Why Data Science? 

➢ Industries require accurate data to help them and make careful decisions. 

➢ Data Science churns raw data into meaningful insights and provides it to 


➢ Companies use data or meaningful insights to analyze their marketing strategies and make better advertisements. 

➢ Improves business, society or performance by gaining knowledge from data. 

➢ Take real-time decisions. 

➢ Make each dollar count and increase the return of investment. 

➢ Builds confidence in business decisions. 

Life Cycle of Data Science 

Phase 1: Define Problem 

Data Scientists do not start with the Data. They start with the problem. You should well- defined problem which contains its solution within it and it makes the problem easier to solve. If you define a problem effectively then it will help you in saving your time and your resources. 

Phase 2: Collect Data 

Data Collection is the process of gathering information on variables which are data requirements. You have to emphasis on ensuring accurate and honest collection of data such that the related decisions are valid. You should gather and scrap the data which is necessary for your project. 

Phase 3: Data Cleaning 

The data collected may be incomplete and may contain errors. The duplicate values should be discarded from the data. For data cleaning, you should fix the inconsistencies within the data and handle the missing values. Data cleaning helps you in making the data effective and accurate. 

Phase 4: Analyze Data 

You can analyze data through various techniques. The analyzed data will help you to understand and interpret the data efficiently. Through analyzed data, you can derive conclusions that will be required in further phases. The best way to analyze data is through data visualization which can be in the graphical or in chart format. Statistical data models can also be used which includes regression analysis and correlation. It includes methods like logistic regression, decision trees, random forest, and neural networks. 

Phase 5: Interpret Result 

The results which came through analyzing data are to be reported in a particular format as required by the industry person. The interpreted results can be in the form of data visualization through charts and graphs. Through these charts and graphs, you can get insights and will help you in marketing strategies. 

What skills need to be a DATA SCIENTIST? 

➢ Strong knowledge of Python, SAS, R. 

➢ Hands-on experience in SQL database coding. 

➢ Knowledge of machine learning. 

➢ Ability to work with unstructured data from various sources like video and social media. 

➢ Understand multiple analytical functions. 

Data Scientist is a person who is a part analyst who makes the use of his technical and analytical abilities to extract meaning and insights from massive data sets. 

Data Scientist helps in increasing data accuracy, reducing costs and developing strategies. 

Python VS R for Data Science 

Python is great for Machine Learning and Deep Learning. R is good for statistical analysis of data.

The fact is that learning both tools Python and R, and using them for their respective strengths can only improve you as a data scientist. Versatility and flexibility are traits of a data scientist in their field. The python vs. R debate makes you stick to one programming language. You should look beyond it and learn both tools for their respective strengths. Using more tools will only make you better as a data scientist. 

Top Application Areas

➢ Digital advertisements 

➢ Internet Research 

➢ Real-Time Predictive Analytics 

➢ Recommendation Engines 

➢ Cyber Security 

In the end, it won’t be wrong to say that the future belongs to the Data Scientists. It was predicted that there will be a need of around one million Data Scientists. Working on more and more data will provide you with opportunities to solve problems and make accurate decisions. And hence Data Science will fulfill all your dreams once you become a successful data scientist. 

Written By: Mansi Mahajan

IEEE Member No: 96171462