*This article was published as a part of the Data Science Blogathon.*

Data Science and its applications first caught my attention in 2016 when I was working as a Digital Marketing specialist in a private company. Plenty of people, including me, had switched to placing orders online through e-commerce companies like Myntra, Jabong & Amazon because they were extremely convenient and user friendly. One thing that caught my eye was the unique recommendation system they had put in place, for example, if I am ordering a suit piece, they would recommend me pretty dupattas. Being in the digital marketing industry, I was aware of the analytics and ad re-targeting that took place while surfing through products. Still, this particular recommendation system immediately caught my attention.

As I started exploring this topic, I unraveled the mystery behind this magical phenomenon; it was none other than Data Science & Machine Learning. I found it pretty amazing how the machines recommend similar products based on the purchases made by different customers who might have bought similar items together. The eCommerce companies majorly rely on a recommendation system that allows them to suggest the user similar products based on past searches and purchases made by other users.

Although I had made up my mind to delve into the domain of data analytics and data science and switch my career, I still wasn’t sure how to get through with it. There were plenty of courses that were available online then which made the journey all the more confusing for me. I subscribed to plenty of online materials and books and six months later I still hadn’t aced the journey towards being a data scientist yet.

Like me, I am sure there are plenty of people who are excited to launch their data science career. Still, due to their work commitments, personal relationships, and non-technical backgrounds have to give it up if they don’t find success within a year. While this is an extremely common phenomenon, it doesn’t have to be this way, if you want to become a data scientist no matter what it takes. I learned it the hard way, but finally, I have discovered a few fantastic ways to jump-start my journey towards data science. So let’s get started then.”

Before understanding the basic concepts and algorithms in data science and machine learning, you must learn a language. I chose to learn the Python language. However, you can learn languages like R, Julia, SAS, etc to start your journey. Learning a language will help you in understanding the algorithms more quickly.

There are times when specific formulas for famous algorithms make absolutely no sense to me. But implementing the algorithm by coding helps me get a clearer picture. You must invest at least a month or two to get comfortable with coding. I recommend starting with Python as the syntax is easy to understand, and its libraries come in handy while you tend to implement machine learning algorithms.

- Learn Python Fundamentals: If you happen to learn yourself then start with learning Python Fundamentals. Get comfortable with coding in a particular IDE like Jupyter or Pycharm. Both are good in their own ways.
- Learn & practice python projects and solve problems using the concepts you have learned. You can start by building a project that analyses your daily spending habit from platforms like Amazon, Big Basket, etc.
- Learn Web Scraping with Python: It is absolutely essential to learn web scraping as it helps you collect data and analyze it for your own benefit. I was working on a Canadian project wherein I had to scrape details of electricians from the Toronto region so I used web scraping to scrape the data from a site named kijiji.ca. It was very interesting to extract all the reliable data and then work according to my company requirements.

You must be comfortable with statistics as statistics are implemented to ace business problems in daily lives. You must also get familiar with data science algorithms as these come in handy. Simultaneously, you happen to solve any business problem or implement its usage in any data science-based project.

You must also have a clearer understanding of the difference between classification, regression, and clustering problems as with this you can build a separate data science model. Based on the type of problem you encounter, the knowledge of these three machine learning techniques come extremely handy.

Even if you are not fond of statistics, you still have to learn statistics to ace your data science journey. I was never a fan of statistics, however, I found out that without it I might not be able to understand the advanced concepts. Statistical methods have been majorly used to ensure that the data collected by you has been interpreted correctly. Primarily, the statistical analysis helps in finding meaning to meaningless numbers in the data.

As time went by I began to enjoy learning statistics for data science. Here’s what you need to learn for data science:

- Statistics and probability theory
- Probability distributions
- Hypothesis testing
- Statistical modeling and fitting
- Machine Learning
- Regression analysis
- Bayesian thinking and modeling

There are plenty of sources to learn Statistics from. I recommend learning the concepts from Udacity and Khan Academy. If you find it boring then the Youtube Channel by Stats Quest is a fun way to learn statistics. If you are already enrolled in some course, then religiously follow their curriculum to have a better understanding.

Learning mindlessly can yield little or no results as there is no external motivational factor driving you to move ahead. If you plan to transition your career, if you are already familiar with data science and machine learning, make sure that you plan your study ahead of time. It’s essential to build a course plan and abide by the same until you complete it.

If you are planning to start your data science journey from scratch, you must enroll yourself in a trustworthy course and follow their guidelines. Although there are a plethora of courses out there, companies like Analytics Vidhya have launched an interesting line of courses which also give a job guarantee if you follow their plan and schedule diligently. It is an excellent way to stay motivated and complete your data science journey.

Please stick to one particular plan and don’t forget to revise and learn new concepts daily.

There are plenty of free online groups in data science, wherein you can get plenty of resources and help online. Once you get comfortable with coding and implementing concepts, don’t forget to share your doubts and concern if you get stuck. The experts out there will always be there to support you and solve your problems.

Reviewing already existing projects and checking their code from start to finish can bring an entirely new perspective to your pace of learning. Just theoretical knowledge is not enough; implementing the same live projects can speed up your career very fast. To better understand, you can always start with a project with a fair share of knowledge. For example, I worked in the finance sector, so I chose to start with a business problem that dealt with my area of expertise. With my domain knowledge and data science skills, I could understand the ongoing concern that the company was facing. With my data science skills, I knew exactly what model implementation could yield results.

Well, that’s how I started my journey. I am extremely happy with the progress I made, and I have seen my fellow mates who have worked towards their passion for data science and have successfully switched their career in data science.

Hi, I am Ananya, & I am a passionate blogger and a business analyst. My data science journey has just begun, and I am enjoying every bit of it. I get to work on two of my best domains: data science and e-commerce, and I can’t be more proud of it.

*The media shown in this article are not owned by Analytics Vidhya and is used at the Author’s discretion.*

In my view this article discusses in nutshell about the basic concepts of Datascience. Hence this article can effectively guide the starters for the basic concepts about Datascience & how it functions.