The Perfect Roadmap to Learn Data Science in 2024

Vincent Favour
8 min readDec 16, 2023

A data scientist is someone better at statistics than any software engineer and better at software engineering than any statistician

If you’ve clicked to view this write-up, it’s likely you see data science as a path you want to explore or even transition into. This guide is your personalized roadmap to stepping into the shoes of a data scientist in 2024, which is just around the corner.

Without any further ado, I will friendly guide on this adventure

Businesses need to make smart decisions to grow, and Data Scientists play a crucial role in this process. They analyze data to help businesses make the best decisions and promote growth. As digital transformation continues, the demand for Data Scientists is increasing across all industries.

So with that being said, we know that a data scientist is someone who analyzes data to help make better decisions. They find patterns, draw insights, and provide valuable information that businesses or organizations use to improve and grow.

Image Credit: 365 Data Science

The truth is that, unlike other software skills such as web development, mobile development, UI/UX design, and more, data science comes with prerequisites. One cannot just wake up from the street one day and pick up a YouTube tutorial to learn data science. Yes, there are resources available, but it’s not as simple as it may seem.

Why, you may ask?

When industries seek to hire people in this field, qualifications become crucial. We often see requirements such as an undergraduate or postgraduate degree in a relevant discipline like mathematics, statistics, computer science, economics, information management, business information systems, etc.

To become a data scientist, you must take education seriously, potentially advancing to higher levels such as a master's or even a Ph.D. The demand for qualifications in this field reflects the complexity and responsibility that come with analyzing and interpreting data to make informed decisions for business growth.

So if you are an undergraduate or a graduate from a technical or non-technical background, here are the things you should strengthen yourself in.


Before diving into the world of data science, it’s important to get familiar with some basic statistical terms. Think of these terms as the building blocks that help us understand and make sense of data. We use them to talk about things like groups of data (populations), smaller groups we study (samples), and the different things we measure (variables). There are also handy tools like mean, median, and mode that help us describe data patterns.

And if you want to see how things are connected, that’s where correlation and regression come in. Correlation helps us understand if two things are related — like if studying more leads to better grades. Regression goes a step further, letting us predict one thing based on another — like predicting future sales based on past data. These might sound complex, but they’re like your data superpowers, helping you uncover hidden connections and make smarter decisions.

So, understanding these basic statistical ideas isn’t just for experts — it’s your key to making sense of data, no matter what tools you’re using.

I’m sure many people might feel a bit scared because of the math and stats involved.

2. Communication and Visualization Tools

Image by Yazdi

The next step involves learning dashboard and visualization tools such as Excel, Tableau, or Power BI. These tools act as powerful aids, allowing you to visually represent and understand patterns in your data. They serve as practical instruments, helping you craft clear and meaningful images from complex information. Learning to use these tools is akin to acquiring a valuable skill, empowering you to explore and interpret data with precision.



  • Hotel Banking Dashboard
  • Road Accident Analysis
  • Sales Dashboard
  • Netflix Analysis Dashboard
  • Uefa Champions League Analysis Dashboard

3. Version Control

Image Credit: Zhan

It’s crucial to explore version control, particularly with tools like Git and GitHub. This not only ensures organized and efficient project management but also allows you to showcase your work to potential collaborators or clients.

Learning how to document your code is an essential skill for a data scientist. Proper documentation not only helps you keep track of your work but also makes it accessible and understandable to others.

Click here to dive into the art of code documentation and elevate your data science projects to a professional level.

4. SQL (Sequential Query Language)

After getting comfortable with tools like Excel, the next skill to master is SQL (Structured Query Language). SQL is the language of databases and is crucial for efficiently managing and querying data. With SQL, you can organize, retrieve, and manipulate data seamlessly.

Example SQL Commands:

-- Creating a form to insert data into the 'employees' table
INSERT INTO employees (employee_id, first_name, last_name, salary)
VALUES (1, 'John', 'Doe', 50000);

-- Creating a form to retrieve data from the 'employees' table
SELECT * FROM employees WHERE first_name = 'John';

Why Learn SQL?

  1. Database Management: SQL is used to manage databases, making it easier to organize and access large sets of information.
  2. Data Retrieval: Learn to fetch specific data from databases using SQL queries. It’s like having a targeted search tool for your data.
  3. Data Manipulation: SQL allows you to insert, update, and delete data, providing control over the information in your databases.

Start by understanding basic SQL syntax, then gradually explore more advanced topics such as joins, subqueries, and database design principles. This foundational knowledge will serve you well as you continue your journey into the world of data science.”


For your project, consider combining your SQL knowledge with a visualization tool like Excel, Tableau, or Power BI. This dynamic duo allows you to not only manage and query databases effectively but also present your findings in a visually compelling manner. Choose a dataset that interests you — it could be anything from finance to sports.

5. Python Programming Language For Data Science

Image Credit: Papassidhi

Python handles large datasets effortlessly, making it ideal for tackling big and complex information. It’s the go-to choice when you need speed and scalability, enabling advanced data analysis and machine learning tasks with ease.

Python has special tools like Matplotlib and Seaborn that make it easy to create cool charts and graphs. There are even fancier tools like Plotly and Bokeh that let you make interactive charts — imagine your data telling a story that people can explore!

To kick off your Python journey, you’ll start with the basics — learning about things like variables, data types, and how to make your program do what you want. And guess what? Python also plays super well with data tools like Pandas, making your whole data analysis journey even more powerful.

6. Machine Learning

Image from google

When you hear about machine learning, it might sound like a daunting task, but let me break it down for you. Imagine teaching a computer to learn from examples, just like how you’d show a friend to recognize cats from dogs by showing them pictures. That’s essentially what machine learning is — it’s a way for computers to learn from data without being explicitly programmed.

So, instead of giving step-by-step instructions, we feed the computer lots of examples, and it figures out how to make predictions or decisions on its own. It’s like having a smart assistant that learns and gets better at tasks over time. Whether it’s predicting if it will rain tomorrow or understanding what movies you might like, machine learning is like giving computers the power to learn and make smart choices on their own.

To embark on the exciting journey of machine learning, you’ll want to become pals with Python. Why Python? Because it’s like the superhero sidekick for machine learning enthusiasts. Python offers user-friendly libraries, such as Scikit-Learn and TensorFlow, that make diving into machine learning a breeze.

7. Model Deployment Techniques

When you create a smart machine-learning model on your computer (like making a new character in a game), the next step is to let it go out into the real world and start helping people. We do this by deploying it, which is like giving it a job to do.

Instead of keeping it in the computer where you created it, deployment lets it step out and use its smarts to make predictions or answer questions for others. It’s like turning your virtual friend into a real-life helper who can do cool stuff for people outside of your computer.

You can turn your machine learning models into practical applications for the real world, whether it’s creating a web-based interface using Streamlit or Flask or deploying your model on a mobile app using TensorFlow Lite or ONNX. These tools and libraries play a crucial role in making your models accessible and useful beyond the coding environment.

8. Deep Learning

Imagine you’re teaching a computer to recognize things, like cats in pictures. In traditional machine learning, you’d show the computer different features of a cat — like its ears, whiskers, and tail — and it learns to identify a cat based on these features.

Now, enter deep learning — it’s like telling the computer, “Hey, figure out the important features yourself!” Instead of giving explicit instructions, we let the computer learn intricate patterns and features on its own. It does this through layers of interconnected nodes, mimicking the way our brain works. Each layer learns a specific aspect, and as you stack more layers, the computer gets better at understanding complex relationships in the data.

So, deep learning is like giving the computer a powerful brain to decipher and understand intricate patterns in data, making it especially powerful for tasks like image and speech recognition. It’s like teaching the computer to see and hear things on its own!

Embarking on data science is like a step-by-step adventure. . It requires dedication, persistence, and curiosity, but the satisfaction of turning data into real-world impact makes the journey both challenging and immensely rewarding.

Before you go!

  • Stay tuned for more insights! Follow and subscribe.
  • Did you see what happens when you click and hold the clap 👏 button?



Vincent Favour

Talks about Programming, Data science, Inspiration quotes and Academic Affairs. Reach me on twitter : @ogboifavour