Logistic Regression: Is it a spam message?

By now we have gotten an intuitive understanding of what regression is about. To quickly restate what we are doing, we are taking a bunch of input variables (variously called independent variables, covariates or features depending on whether you’re reading a statistics, computer science or machine learning text) and output variable (the response variable, dependent…

Linear Regression: Predicting House Prices

I am big fan of Kalid Azad writings. He has a knack of explaining hard mathematical concepts like Calculus in simple words and helps the readers to get the intuition behind the idea. Couple of days back I was reading his book on Calculus. I came across the following passage in the book— What’s a better learning…

Why Machine Learning?

A good friend of mine recommended me to read the book The Craft Of Research. It is a fantastic book and it shows how to go about conducting a research and present it in a structured way so that your readers can understand and appreciate your research. I highly recommend this book for almost anyone who…

Amazon knows what I like

I buy a lot of books from amazon.com. You can view my online bookshelf here. One of the reasons I like amazon.com is because of its recommendations engine. Few days back it recommended me the book Thinking Fast and Slow. It is one of my favorite books. It not only recommended the book but it also…

Tf-Idf and Cosine similarity

In the year 1998 Google handled 9800 average search queries every day. In 2012 this number shot up to 5.13 billion average searches per day. The graph given below shows this astronomical growth. Year Average Search per day 1998 9800 2000 60000000 2007 1200000000 2008 1745000000 2009 2610000000 2010 3627000000 2011 4717000000 2012 5134000000 The…

Netflix knows what I like

I am a Netflix subscriber. Every time I go to their site it will recommend movies I might like. Most of the times its recommendations are very good. How does it know what I like? I do not know how the actual algorithm is implemented. But I know some of the basic concepts behind this.…

Non Personalized Recommenders

In non personalized recommenders everyone gets to see the same recommendation. The site does not know who you are. If I go to amazon.com as an anonymous user it shows items that are currently viewed by other members. This is one example of a non personalized recommendation. There are two variations in this – Predictions…