2 thoughts on “That’s like so random! Monte Carlo for Data Science

  1. Hi Corey Chivers,

    Thank you for this amazing article.
    I have always been fascinated by randomized functions and how they can help us in building models. The use of ”obscure statistics” applied to prediction is very interesting and can sometimes be the most relevant way to understand processes. Moreover, I am still mind blown by the help of “hazardous” which can be sometimes and for a certain “level of knowledge” the best way to predict phenoma induced by unknow laws or to test and improve a model that we are working on.
    Bring aleatory to be able to create intended representation is fabulous.

  2. If you’re going to do Monte Carlo integration, realize that the randomness isn’t as important as “good sampling” of your distribution – investigate edquidistributed sequences (on a (0,1)^n hypercube, run through the inverse CDF). In a quantifiable sense, each additional point brings as much information as possible to the table.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s