DEV Community

Cover image for What you should know about Data Science to get started.
Anastasiia Leskiv
Anastasiia Leskiv

Posted on

What you should know about Data Science to get started.

Data science is a very trendy topic/profession nowadays.A lot of people are interested in this field but really not sure what Data science actually means. This article is all about what is Data science and why it is important for a company to have one.
So, let's start with the really first question you ask yourself when you hear about this field. What is Data Science?
The definition you can see on Google would be something like Data science combining domain expertise, programming skills, and knowledge of mathematics and statistics to extend manful insight from data. Which is a good definition but what does exactly that mean?

When it comes to Data Science there are 5 main stages.

  1. Capture
    This is the process of extracting information from any type of documents and converting it into a format readable by a computer.

  2. Maintain
    That is when we are cleaning, correcting, ingesting, storing, organizing and maintaining the data created and collected by an organization.

3.Process
Systematic approach to solving a data problem. Choosing a strategy we will use to solve the problem.

4.Analyze
Process when applying statistics and logic to describe and illustrate, condense and recap, and evaluate data.

  1. Comunicate When we do data visualization, making decisions, and reporting our findings to clients or business people in order to help them make strategic and business decisions.

The second very important question you should ask is what problems can data science solve?
There is 4 main problems that data science can solve:

  1. Regression
    Regression is answering the question: how much or how many? It used to predict a continuous value. For example, what would be the sale price of a house?

  2. Classification
    Classification is answering the question: which category? It used to predict which category something will fall into.If you're trying to figure out whether a client is likely to default on a loan or which of your products a customer is likely to prefer, you're dealing with a classification problem.

  3. Anomaly detection
    Anomaly detection is answering the question: if this is weird? It identifies fraud and is used to find unusual patterns that do not conform to expected behavior.

4.Recommender systems
Recommender systems answer the question: which item would a user prefer? It used to predict user preferences towards a product/service. For example when we watch Netflix we can notice a section like "recommended for you because you watched ..." This is exactly what recommender systems are.

The work data scientists do is very interesting and helpful. It helps to improve businesses and first of all quality of lives. In my opinion data science will always be relevant, in the future it will be even more necessary for every company since we live in the technical world and there are no limits in development. I hope my blog was interesting, informative, and inspiring.

Top comments (0)