inventory_featured_image

Our Data Science Pipeline: Machine Learning Meets Traditional Business Intelligence

The role of a data science team varies from one organization to the next. Some organizations require a “traditional” business intelligence framework: one in which historical data is turned into actionable insights. Others run impressively complex machine learning algorithms all day long – sometimes in realtime – in order to transform the most up-to-date data…

donor_retention_arrow

Understanding Why Donors Do (Not) Return

Recruitment and continued engagement of donors is critical for the success of crowdfunding communities, such as DonorsChoose.org. With donor attrition rates above 70%, a significant challenge for online crowdfunding platforms as well as traditional offline non-profit organizations is the problem of donor retention — getting donors to continue to make donations year after year. Increasing…

kickstarting-teachers

Kickstarting Teachers

One of our many goals this year is to increase the success rate of teachers and schools that have never been funded. To do so, we added a new tile to the homepage that links to those teachers or schools with live projects. For this test, we tried a few different text and photo combos….

Recession Impact on Schools

How Did 2008 Recession Impact Schools?

DonorsChoose.org works at addressing educational inequity, which explains our interest in analyzing broader macro economic trends. This time, we were curious about how the great recession of 2008 impacted what teachers from high-poverty versus low-poverty classrooms were requesting on our site. We felt the data represented a broader economic trend as over 50% of America’s…

redshift_cover

Analytics in Redshift: The Migration Script

Inspired by posts from Bitly and Airbnb data teams on Redshift as a replacement for Hadoop we decided to give it a try. And we loved it. We loved it so much that we wrote a Postgres to Redshift migration script and open-sourced it. Why Redshift? We needed speed: from our partnership team doing reporting, product…

error

Errors drive us crazy

Errors driving you crazy? Errors drive us crazy too, especially the small ones. It has come to our attention recently that a larger than expected amount of donors using our website on desktop forget to select an expiration date! It’s quite odd considering that all online payments today require this information to be entered, and…

No School Left Behind

No School Left Behind: Get Your School on the Map

Through the incredible generosity of over 1.5 million citizen philanthropists, DonorsChoose.org has supported over a quarter billion dollars in classroom supplies for schools across the nation. But we have an even bigger goal in mind: to reach 100% of the nation’s highest poverty schools. We identify schools in which over 65% of students are eligible…

names_wordcloud_cover

What’s in a Name?

Inspired by Reuben Fischer-Baum’s maps of popular baby boy and girl names, we decided to create our own animated map of popular donor names across the United States, depicting shifting trends in names since we launched. We find this name map interesting for two reasons. First, it shows the growth of DonorsChoose.org – we might…

malefemale

Male Teachers Get More Donations Than Female Teachers. Why?

Guest post: Greg Laughlin is CEO of Statwing, an easy-to-use data analysis tool. Male teachers fundraise on DonorsChoose more successfully than female teachers. The effect isn’t huge, but it’s there. We wanted to figure out why. Take a look at the differences: See these results in Statwing, along with statistical results. See these results in…

techiness

“Techiness” of Tech-Savvy US Cities

Drawn from multiple online sources, we’ve devised a list of the most tech-savvy cities in the US. Our data shows that, interestingly enough, there are 2 breeds of Tech-savvy cities: those that have a much lower emphasis on technology-related projects compared to the rest of the US and those that have a much higher emphasis…