The Powerball dream is just over. Only three people won the jackpot of $1.5 billion while many of us were left with a $2 transaction on our account. This weekend, I found a database for New Yorker’s spend on the Powerball tickets since Dec 2015 and visualized how much New York people spent on the $1.5 billion jackpot. Here comes the map:

Read the Post Visualization of New York Spend on the $1.5Billion Powerball

In this post, I want to share with you some R codes to perform multivariate regression, penalized regression and classification partition analysis with a dataset that contains zipcode level Starbucks, McDonald location information as well as demographics of local population in New York State. First an overview on the data set and list of variables:

Read the Post Analyzing New York McDonald and Starbucks Location with R

It has been a few months since our new OGS website came alive ( check it here: Before we accumulate enough data to analyze the page performances, we surveyed over 500 students before and after the redesign took place and here is an infographic for the result I want to share with you. If you are interested, here is the original post on our tumblr blog. Hope you enjoy this post and infographics I made.

Read the Post Data for NYU OGS Website Redesign Project

I want to share with you how to do data scraping with R. R has few wonderful packages such as the XML, that could help you grab any data you want from a web page. A handy document to keep on your desk when you do scrapping is an instruction to XML package from Gatson.The first thing you need is a url. Let’s take IMDB “The Intern” page for an example today. Let’s give this link address a name.

Read the Post Scrape IMDB “The Intern” Movie Data with R

Hi there,

In this post I would like to share with you how I worked on Email A/B testing for NYU.

As a member of communication team in Office of Global Service, my main mission is to improve performances of communication channel in our office. Email is one very important asset in our communication process. We email to over 10,000 students biweekly throughout the school year. First, let me talk about few things on testing:  Read the Post Email A/B Testing for Higher Education

Since the very beginning of digital marketing, an inevitable topic in competitive analysis is data scraping. The best way to know your competitor’s pricing and strategy is to scrape their data directly from their website. You probably have seen hardcore scrapers tangling with python and R, which I will share few experiences on in upcoming weeks. However you know how hard it is to pick up a fresh technical language that you probably won’t need in your following lifetime. So in this post, I want to share two tools that I personally like when doing no-hardcore scraping: and Parsehub.

Read the Post Dummy Web Data Scraping with and Parsehub

Hello there,

For last few days, I have been eating and sleeping with R( partly because I am doing homework for one edx course that I signed up to for machine learning). One week ago, Riot just released an API challenge to its gentlemen-thinking fans(like you and me), So I feel it’s time to get on top of this topic and introduce some work I have done with Riot game API. I have to warn you here that I am not a geek gal so my code may not be enough to build out a super fancy app that I can take to the API challenge. I do what I do for fun. Enjoy and “Demacia”!

Read the Post R code for Riot League of Legend API Challenge