- data-science random-questions statistics
Statistical bias could creep up on our analysis and caused us to communicate the wrong insights and drive home the wrong conclusions.
- statistics test-your-knowledge
This post is displayed directly from my notebook @ Github. You might want to view it on Github directly if it doesn’t render properly on your browser.
Let's say we have 1 million app rider journey trips. We want to build a model to predict ETA after a rider makes a ride request...data-science machine-learning test-your-knowledge
..how would we know if we have enough data to create an accurate enough model?
Let's say you have a categorical variable with thousands of distinct values, how would you encode it?machine-learning test-your-knowledge
One-hot encoding is out of the question since a large number of distinct values will result in large dimensionality problems(Curse of Dimensionality) in modeling stage.
Let's say we want to build a model to predict booking prices for a hotel booking company. Between linear regression and random forest regression, which model would perform better and why?machine-learning statistics test-your-knowledge
Before we quickly answer “Random Forest”, let’s take a step back and put on our structured thinking cap to ask ourselves why and perhaps in real life, companies might take the other choice.
- data-science python statistics
This is a hands-on guide to hypothesis testing, where we use both “hand coded” and the common statistical libraries, to calculate different statistical test.