ICDM 2018 Workshop on Data Mining for eLearning Personalization

We are excited to co-organize a workshop at ICDM 2018 on applications of data mining for education!

The ICDM 2018 Workshop on Data Mining for eLearning Personalization will be held in conjunction with the International Conference on Data Mining (ICDM) on November 17, 2018 in Singapore. The workshop will bring together researchers, software engineers, educators, and others conducting cutting-edge work on data-driven personalization in the online learning context to discuss how we can develop models for the process of (human) learning, and use these models in the development of data-driven online learning systems that personalize the experience and improve outcomes.

…

This post was co-authored with Duncan Gilchrist and is Part 3 of our “Best of Both Worlds: An Applied Intro to ML For Causal Inference” series (Part 1 here, Part 2 here). Sample code, along with basic simulation results, is available on GitHub.

We’re grateful to Evan Magnusson for his strong thought-partnership and excellent insights throughout.

This post covers an exciting set of methods at the intersection of statistics, econometrics, and machine learning that allow data scientists to leverage vast repositories of AB results to estimate the causal effect of specific user behaviors on outcomes.

You probably have intuition that…

This post was co-authored with Duncan Gilchrist and is Part 1 of our “Best of Both Worlds: An Applied Intro to ML for Causal Inference” series (Part 2 here).

We’re grateful to Evan Magnusson for his strong thought-partnership and excellent insights throughout.

Over the last couple years, we’ve been excited to see — and leverage — a range of new methods that significantly improve our ability to glean causal relationships from data, especially big data. Many of these marry the best of machine learning and econometrics to unlock deeper and more correct inference. …

How female instructors can help close the gender gap in STEM

Coauthored with Vinod Bakthavachalam, Data Scientist at Coursera

Coursera was founded on the belief that education can help anyone, anywhere improve their career and life outcomes. We strive to enable global, inclusive access to high-quality education — especially for those who have historically been underrepresented in university classrooms. In honor of International Women’s Day on March 8th, we’re thinking in particular about how we can support and encourage female learners in fields traditionally dominated by men.

Only 28 percent of graduates from U.S. STEM (science, technology, engineering, and mathematics) degree programs are female; given that almost 75 percent of high…

Sourcing, hiring, and growing female talent

Here at Coursera, we are proud to have a data science team that is nearly half female. The problems we’re tackling demand creative approaches and, as the literature consistently shows, diversity unlocks innovation.

Yet only 16% of technical roles at major tech companies are held by women. What lessons have we learned in building our team?

Sourcing diverse talent

Diversity — including gender diversity — demands conscious and consistent efforts to source the right mix of talent. Consider the very top of the recruiting funnel and its three main pipelines: organic applicants, referrals from existing employees, and sourced candidates.

• Organic…

Lightning Talks @ Coursera

Join us January 18 for the Women Who Code Silicon Valley Data Science 2017 kick-off! Lightning talks on Data Products, A/B Testing, Career, & more by Data Science women at Coursera. RSVP here.

Here are slides from today’s Causal Inference in Tech workshop at the Open Data Science Conference. Thanks to all who participated!

Evidence from three field experiments

Most workers in the U.S. find their jobs through friends and relatives, and companies are more likely to hire applicants who have been referred. In a series of three experiments in a real labor market, Harvard economist Amanda Pallais and I show that this is not just nepotism: referred workers are actually more productive and have lower turnover than non-referred workers.

By hiring referred and non-referred applicants and comparing their performance on different tasks, we show that applicants who are referred are significantly better workers in ways that are not apparent from resumes alone. In…