Himabindu Lakkaraju


428 Morgan Hall

I am a postdoctoral fellow at Harvard University (jointly with Business School and Computer Science).

Prior to this, I was a PhD student in Computer Science at Stanford University, advised by Prof. Jure Leskovec. I also frequently collaborated with Prof. Cynthia Rudin, Prof. Jon Kleinberg, Prof. Sendhil Mullainathan, and Dr. Eric Horvitz. My PhD research was generously supported by a Stanford Graduate Fellowship, a Microsoft Research Dissertation Grant, and a Google Anita Borg Scholarship.

I develop computational methods to make the practice of machine learning more transparent, reliable, fair, and socially relevant. My research finds applications in domains involving high-stakes decisions such as law, health care, public policy, business, and education.

My research combines techniques from machine learning, data mining, econometrics, and computational social science to address various fundamental questions pertaining to human and algorithmic decision-making:

  1. How do we build interpretable models that can aid human decision-making?
  2. How do we evaluate the effectiveness of algorithmic predictions and compare them with human decisions?
  3. How do we detect and correct underlying biases in human decisions and algorithmic predictions?
My research proposes novel computational frameworks which address the above questions by effectively handling the core underlying challenges such as missing counterfactuals and presence of unmeasured confounders.

For more details, please refer my CV.