Tool: Microsoft Excel | Type: Exploratory Data Analysis | Records: 1,026 customers

OVERVIEW I worked with a retail dataset of 1,026 customers to figure out what kinds of people are most likely to buy a bike. The dataset had details like age, income, commute distance, occupation, education, marital status, and region, plus a column showing whether or not they actually purchased a bike. The goal was to spot patterns and help the business understand who to target.

WHAT I DID – Started by cleaning the raw data — standardised abbreviations (e.g. 'M' → 'Married', 'F' → 'Female'), removed duplicates, and confirmed there were no missing values. – Created a new Age Brackets column using a nested IF formula to group customers into Adolescent, Middle Age, and Old — made the analysis much cleaner. – Built pivot tables to cross-reference purchase behaviour against commute distance, age group, income, and gender. – Pulled everything into a dashboard with charts and slicers so you can filter by region or marital status interactively.

WHAT I FOUND – Middle-aged customers (31–54) were by far the most likely to buy — nearly 50% purchase rate in that group. – People commuting 2–5 miles had the highest conversion (54%), while those commuting 10+ miles rarely bought (around 21%). – Buyers earned slightly more on average ($57,475) compared to non-buyers ($55,028) — not a massive gap, but a consistent signal. – Older customers (55+) showed the lowest interest — only 25% purchased, which could mean the product or messaging isn't resonating.

TAKEAWAY The clearest profile of a likely buyer is someone in their 30s–40s, earning a moderate-to-good income, and commuting a short distance. That's who the business should be talking to first.