LEGO Data

Data for LEGO sets from 1991 to 2023.

The Questions

  1. How does the price per piece affect the rating of a set?

  2. How do the number of minifigures in a set affect the rating of a set?

The Data

  • The data set I used was from Kaggle by Alex Racape.

  • The data from Kaggle contains every LEGO product from the 1975 to 2023.

  • The data I worked with on Google Sheets contains both the original and my cleaned version.

Cleaning

  • I added a column for price per piece.

  • Eliminated rows where the set had no price, rating, or piece count.

  • Hid columns that would not be used.

  • Changed blank cells in the minifigure column to zero.

  • Formatted data and columns to be consistent.

Analysis

Question 1

How does the price per piece affect the rating of a set?

  • As the rating increases the average price per piece in a set generally decreases.

  • This is shown even more when we look at the a scatter plot of the data.

  • We need to keep in mind that the data on the higher and lower ratings do not have as many sets to look at.

Question 2

How do the number of minifigures in a set affect the rating of a set?

  • Looking at the pivot table we can see that there are a large amount of sets with zero minifigures.

  • Once we pass 9 and 10 minifigures the amount of data we have is reduced.

  • We still see a slight increase of rating when the number of minifigures has increased.

  • This slight increase can be seen in the graph below but without more data in the higher minifigure count it is hard to say if the trend would continue to increase or not.

The Answer

  1. We can see that the lower the price per piece in a set the better the set is rated.

  2. 5 to 6 minifigures in a set is going to give the set a higher rating on average.

Actionable Outcome

Based on the data actionable steps LEGO could take moving forward would be as follows.

  • Minimize price per piece for higher customer satisfaction on a specific set.

  • 9 to 15 cents per piece is optimal for a higher set rating.

  • 5 to 6 minifigures in a set for higher customer satisfaction on a specific set.

  • More testing on sets with higher minifigure counts.

  • 7 - 10 minifigures in a set could give better ratings and would be the starting point to looking at more data.

One of the reasons I decided to this project was because I am very passionate about LEGO!

Below are some sets I have built and part of my collection.