Big Data & Data Science (Years 10–11) — Computer Science

What makes data 'big' through the 3 Vs of Volume, Velocity and Variety, where big data comes from, how data science follows a collect-clean-analyse-visualise pipeline to turn data into decisions, its real uses, and the privacy concerns it raises.

Every time you tap, scroll, buy, message or walk past a sensor, you leave a tiny trail of data. Multiply that by billions of people and devices, all day, every day, and you get a flood so vast and so fast that ordinary tools simply drown in it. That flood is big data — and the job of squeezing something useful out of it is data science.

Why this matters: Big data already picks the next video you watch, helps doctors spot disease, decides which products a shop stocks and predicts tonight's traffic. It also raises hard questions about your privacy. Knowing how data becomes decisions — and who is watching — is central to understanding the modern digital world.

What makes data "big"

Big data means data sets that are too large, too fast or too varied for normal tools like a single spreadsheet to handle. It is usually described by the 3 Vs: Volume (a huge amount), Velocity (arriving very quickly) and Variety (many different kinds — text, images, video, sensor readings). A set only counts as big data when the ordinary tools give up.

Big data is defined by Volume, Velocity and Variety — the 3 Vs.

Where it all comes from

The flood pours in from everywhere: phones (location, apps, photos), sensors (weather stations, fitness trackers, traffic cameras), social media (posts, likes, videos) and shops (every scan at the till and click online). Each source is a tap left running, and together they fill the reservoir.

Phones, sensors, social media and shops all feed the big-data store.

Data science: turning data into decisions

Data science is the work of finding patterns and insights in data so people can make better decisions. It usually follows a pipeline: collect the data, clean it (fix errors and remove junk), analyse it to find patterns, then visualise the results as charts anyone can read. Cleaning matters most of all — messy data gives useless answers.

The data-science pipeline: collect, clean, analyse, visualise.

Finding the pattern

The whole point is that a pattern hidden in a scatter of individual points becomes obvious once you have enough of them and the right tools. One shopper buying nappies and wipes together is nothing; a million doing it is a stocking decision. Data science is how that signal is pulled out of the noise.

Scattered points hide a pattern; data science draws it out.

Uses and the privacy price

Use	What the data does
Recommendations	Suggests films, songs or products you may like
Health research	Spots disease patterns across millions of records
Business	Decides stock, prices and what customers want
Traffic	Predicts jams and reroutes drivers

Worked example — how a streaming app recommends: It collects what millions of viewers watch, pause and skip. It cleans out broken records. It analyses the data to find that people who liked show A tend to like show B. It visualises and acts on that pattern by putting show B on your home screen. No human chose it for you personally — a pattern in the big data did.

Common mistake & the privacy price: Big data is not harmless just because it is "only numbers". Combining many small trails can reveal where you live, your health or your habits. Data can be leaked, sold or used to profile you — which is why laws limit how it is collected and kept.

Tip: remember big data by its 3 Vs — Volume, Velocity, Variety — and remember data science as the collect, clean, analyse, visualise pipeline that turns that flood into a decision.