×

Search anything:

Introduction to Data Science

Free book on Dynamic Programming

Get this book -> Problems on Array: For Interviews and Competitive Programming

In this article, we will get to know what data science is, why is it becoming more sought after and also about its importance.

Table of contents

  • What is Data Science?
  • Why is data science important?

What is Data Science?

A collection of facts or raw information is called data. Data science in simple words, is creating new ways of understanding the unknown from raw data and data analysis refers to collecting and manipulating data to derive insights and make predictions. Data science is well-known as the interdisciplinary field that uses mathematics, computer programming and domain expertise in the journey of converting data to knowledge. Building relevant machine learning algorithms and models, data visualization, data cleaning, analyzing data are all a part of data science.

In data science, we come across two broad categories of data: qualitative and quantitative. Quantitative data is specific and measures of numerical facts whereas qualitative data is more subjective and explanatory. A collection of these data are called datasets. Based on these datasets and the problem which we need to solve, we can classify data as big data and small data. Big data are usually large, less specific and are used to make major decisions for the longer run. On the other hand, small data is more specific and are used to make decisions concerning a shorter time period or day-to-day decisions.

Why is data science important?

Almost every field uses data. Scientists estimate that around 90% of world's data has been generated in the last few years. This makes dealing with data very empowering and also making it one of the most valued asset. Data driven business decisions and predictions are more reliable and accurate as they have relevant data to back them up and many organizations take up this approach.

In businesses, almost all their decisions are driven by insights obtained from data. These may be past data, data collected from surveys, observations, etc. Suppose an ice-cream company decides to launch a new flavor. This flavor must be decided based on the flavor profile of the consumers, likes and dislikes of the target audience, insights from previous launches of new flavors and many more. And to maximize sales, the company must sell a greater amount of this flavor in geographic locations where people have shown more affinity towards the chosen flavor, find the most effective marketing technique and also choose an appropriate date of launch ( A tropical flavor is likely to sell more in the summer months rather than the other times of the year and a pumpkin pie flavor is likely to sell more around Thanksgiving ). Businesses make use of K-means clustering models to segment their customers based on their demographic information, geographic location and psychographics to aid the above mentioned process. Exploratory data analysis is also used for summarizing their main findings.

Data Science plays a crucial role in healthcare industry too. Knowing times when there is more likely to be an increase in the number of patients visiting the hospital (like accidents are more prone at night times in a particular locality) would allow the hospital to be adequately staffed to provide necessary help to the patients. Medical image analysis uses deep learning for the image segmentation and in some ways, it has outperformed human experts in its accuracy. machine learning models have helped to identify diseases faster thus enabling doctors to provide the required treatment as early as possible. In case of cancer prediction models, a modified version of logistic regression is used to predict the malignancy or benignancy of the cells. Machine learning models also aid in faster drug production as they are able to predict the reaction of a particular compound in human body instead of the tedious process of lab tests. For example, QSAR (Quantitative structure–activity relationship) models are regression or classification models that are used to identify and summarize relationship between biological activities and chemical structures and also to predict the activities of new chemicals.Now, healthcare has advanced to a point where customer support and assistance to patients are provided virtually which saves the time of patients.

In the transport sector, data science is extensively used for route optimization and optimizing performance of vehicles. Route optimization uses many underlying machine learning algorithms from logistic regression models to artificial neural networks. With the help of reinforcement learning, vehicle manufacturers are able to design self-driving cars. They are also able to upgrade their engine designs with extensive analysis of fuel consumption patterns. Companies like Uber uses data science for price optimization of their services. With data like location, consumer profile and and other economic and logistic indicators, transport companies and vendors are able to pick the best route so that their resources are properly used.

Similarly in banking, data science is used to build fraud detection mechanisms which again makes use of logistic regression. Risk analysis and modeling, managing customer data, predictive analysis are also some applications of data science in the banking sector.

Now that we have discussed some applications of data science in some few essential fields, this would serve as a sneak peek into how data science is used in many other fields present.

As Andrew McAfee, co-director of the MIT Initiative on the digital economy rightly said, " The world is one big data problem".

With this article at OpenGenus, you must have a good Introduction to Data Science.

Introduction to Data Science
Share this