Alright, here we go.
Uhh… okay so apparently I have to explain “What is Data Science” today.
(looks around)
Who the fuck even scheduled this? I was mid-doomscroll.
Anyway. Welcome to the first post of whatever this chaotic series is going to become. If you’re active on Instagram, X, or that one platform your uncle still calls “the Facebook,” feel free to flex your data science journey and tag me. I’ll pretend to care. Maybe.
So. Data Science.
“Data Science is the field of study that uses mathematics, statistics, programming, and domain knowledge to extract meaningful insights from data.”
Yeah. That’s the version you write in your semester exams so the professor doesn’t fail you out of spite. Congrats, you can now copy-paste that into your assignment and die a little inside.
Real talk though?
Data Science is just the process of collecting a mountain of messy, incomplete, sometimes straight-up lying data… cleaning the absolute shit out of it… analyzing it… and then somehow turning it into decisions that make companies money or make your life slightly more convenient (or both).
That’s it. No fancy TED Talk required.
Why does this even matter?
Because data is everywhere now. Your online shopping history, the sensors in your “smart” fridge that’s judging your 3 a.m. Maggi habits, the way you pause on certain TikToks for 0.4 seconds longer than others — everything is being recorded.
Companies use this data to:
- Decide which product to launch next (so they can sell you more shit you don’t need)
- Predict outcomes (weather, stock prices, whether your situationship is about to ghost you)
- Automate processes (self-driving cars that still somehow can’t handle a simple roundabout)
- Personalize experiences (Netflix knowing you better than your therapist, YouTube recommending the same conspiracy video for the 47th time)
The actual steps (the part you should screenshot)
1. Data Collection
Grabbing raw data from websites, databases, IoT devices, or your ex's public Instagram.
2. Data Cleaning
Fixing errors. This is 80% of the job. The other 20% is pretending it was "insightful."
3. Model Building & Analysis
Throwing machine learning algorithms at the problem and praying to the math gods.
4. Communication
Explaining your findings in a way that doesn't make stakeholders fire you.
Where you already see this shit in action
- Healthcare: Predicting disease outbreaks (and somehow still missing the next one)
- E-commerce: Those creepy “you might also like” recommendations that know you better than your group chat
- Finance: Catching fraudulent transactions… while also inventing new ways for rich people to not pay taxes
- Entertainment: Netflix and YouTube algorithms that have more control over your free time than your own willpower
Why should you even care?
- There’s a massive global shortage of people who can actually do this without crying.
- It’s future-proof in the exact same way that “learning how to talk to robots” is future-proof.
Quick note: The full version of this will be available as a downloadable PDF later so you can pretend you studied. I recommend reading these posts while the videos play in the background like the chronically online academic weapon you are.
Alright. That’s the first one.
If this felt like too much chaos for a “what is data science” post… good. That means it’s working.
See you in the next one. Try not to forget everything I just said in the next 11 seconds.