+4 votes
1 view
in Machine Learning by (1.3k points)
edited by

I want to work on bike-sharing data. I want to classify the group of bike users, based on the area they used most to ride bikes. How can group them based on proximity?

1 Answer

+3 votes
by (3.8k points)
selected by
 
Best answer

There are many unsupervised learning algorithms. K-means clustering is most commonly used for grouping of data. In k-means grouping is done based on the similarity of features. It is the simplest unsupervised learning algorithm that solves the clustering problem.

In the bike-sharing dataset, grouping can be done based on ‘proximity of area’ or ‘age’ or ‘gender’ of the bike users. You will find more about this once you implement the k-means algorithm.

You can find more about this algorithm here.

image

It works by dividing a large set of points (vectors) into groups having approximately the same number of points closest to them. Each group is represented by its centroid point, as in k-means and some other clustering algorithms.

Some other fields related to clustering are

  • Marketing

  • Biology

  • Libraries

  • Insurance

  • City Planning

  • Earthquake studies

And many more…

There are many other applications of clustering, depends on the dataset, you want to work on.

...