Machine Learning

Need help with Machine Learning?

Visit Drop-in Hours or Schedule a Consultation: <link to an embedded google calendar OB widget or google form widget>

Below are the consultant we have available with Machine Learning and other expertise listed.

Filtering, Visualizing, and Interpreting Spatial Time Series Data

December 17, 2025

Maksymilian Jasiak

by Maksymilian Jasiak. Spatial time series (consecutive measurements across space and time) are often difficult to interpret, especially when there are many overlapping signals. However, have no fear! Filtering and visualizing can help better interpret and understand the spatial time series data.

Read more about Filtering, Visualizing, and Interpreting Spatial Time Series Data

Digitization of Historical Maps in the Age of AI

December 3, 2025

Elena Stacy

by Elena Stacy. Researchers today increasingly have access to a wealth of tools to streamline or automate labor-intensive data processing and generation tasks. When it comes to mapping, progress has been slower. This blog details the author's experience tackling the digitization of a historical map in the age of AI.

Read more about Digitization of Historical Maps in the Age of AI

A Practical Guide to Shift-Share Instruments (and What I Learned Replicating the China Shock)

November 26, 2025

Jiayu Lai

by Jiayu Lai. Shift-share instruments are among the most widely used tools in applied economics, appearing in labor, trade, immigration, and policy evaluation research. But despite their popularity, many researchers still use them as black boxes — and risk invalid instruments as a result. In this blog post, I unpack how shift-share IVs actually work, why their validity depends on both the “shifts” and the “shares,” and what practical steps researchers should take to check assumptions. I also walk through how I used the Borusyak–Hull–Jaravel (2022, 2025) framework to reproduce the seminal Autor, Dorn, and Hanson (2013) China shock analysis.

Read more about A Practical Guide to Shift-Share Instruments (and What I Learned Replicating the China Shock)

Sahiba Chopra

Data Science Fellow 2024-2025

Haas School of Business

I'm a PhD student in the Management and Organizations (Macro) group at Berkeley Haas. I have a diverse professional background, primarily as a data scientist across numerous industries, including fintech, cleantech, and media. I hold a BA in Economics from the University of Maryland, an MS in Applied Economics from the University of San Francisco, and an MS in Business Administration from UC Berkeley.

My research focuses on the intersection of inequality, technology, and the labor market. I am particularly interested in understanding how to reduce inequality in...

Read more about Sahiba Chopra

Beyond the Hype: How We Built AI Tools That Actually Support Learning

November 12, 2025

Weiying Li

by Weiying Li. What does genuine partnership look like when building AI for education? Working with middle school teachers and computer scientists, we co-designed AI dialogs where teachers are valuable contributors to refine what the AI understands as valuable thinking. Through iterative refinement, teachers identified precursor ideas and observations that predicted future learning, and refined guidance design in the dialog. Our AI dialog sees learning the way teachers do, built through genuine collaboration where both model development, learning sciences theories, and teachers' classroom expertise work together from the start, not just at the end.

Read more about Beyond the Hype: How We Built AI Tools That Actually Support Learning