This exercise helps you practise a real-world way of learning: investigating a skill by exploring how it is used, where it is required, and what evidence proves you can do it. The goal is to understand a skill deeply enough that you can explain it, practise it, and show it in a small project. This is especially useful in data analysis because employers do not only want tools, they want problem-solving ability.
Start by choosing one data analysis skill to investigate. It can be something like data cleaning, data visualisation, EDA, writing SQL queries, building dashboards, or using Pandas groupby. Write a clear definition of the skill in your own words. Then list where the skill is used in real work, such as reporting, customer analytics, finance tracking, operations metrics, or research analysis.
Next, search for 5 to 10 job descriptions for roles like data analyst, business analyst, or research analyst. Note how the skill is mentioned and what tools are connected to it. For example, you may see that “data cleaning” is linked with Pandas, Excel, and missing value handling, or that “visualisation” is linked with Matplotlib, Seaborn, or Power BI. Identify the most common tasks and keywords that repeat across job posts.
After that, create a small practice plan. Choose a dataset and design a mini task that demonstrates the skill. For example, for data cleaning, you can take a messy CSV, fix missing values, standardise categories, and create a clean output file. For visualisation, you can create 4 charts and write short insights for each.
Finally, document your work in a notebook. Write what you did, what issues you found, and what you learned. This exercise turns a topic into an employable skill and helps you build portfolio evidence step-by-step.
