← Tech

Mobile Phones Sales Analysis

Python EDA on the best-selling phones of recent decades, to understand which features actually predict a successful launch.

What it solves

  • Tracks which technical features stopped being differentiators once they became standard.
  • Sets sales volume against price positioning across several decades.
  • Built to answer a concrete launch question, not to describe the dataset.

The best-selling phones of recent decades tell a fairly clear story about what people buy and when they stop caring about a feature. This analysis reconstructs it from the sales data.

The question

If a company is about to launch a new device, what does the historical record tell it? Specifically:

  • Which features were differentiators, and which became table stakes?
  • Where’s the price point that sustains volume without destroying margin?
  • Which patterns repeat across launches that worked?

What the record shows

One dynamic repeats: a feature arrives as premium, becomes expected, and then its absence turns into a reason for rejection even though its presence no longer sells anything. Working out where on that curve a feature sits today is the useful part of the analysis.

The other pattern is the relationship between volume and price, which isn’t linear: there are clear steps where the market widens all at once.

Tools

Kaggle notebook in Python, Pandas for manipulation and Matplotlib for the visualisations. Published and runnable on Kaggle.

Let's work together

A data project, a musical collaboration, or just a conversation? Drop me a line.