Alex Zhao

Hi, I'm Alex. I'm interested in data, politics, and computer vision. Previously, I wrote data stories on federal politics, developed a command line interface in Golang, and did research on recommender systems.

 /   /  Email  /  Resume  /  Clips

I'm interested in computer vision, economics, and recommender systems.

In this work we investigate the extent to which offline metrics predict online performance by evaluating eleven recommenders across six controlled simulated environments. We provide the environments and recommenders described in this paper as Reclab: an extensible ready-to-use simulation framework at RecLab.

We propose a novel group testing strategy which requires only local information about the underlying transmission network.

We present a flexible and at scale size recommendation approach that overcomes some limitations of current state-of-the-art work by building upon the recent advances in natural language processing and casting the size recommendation problem as a kind of “translation” problem (from articles to sizes) using attention-based deep learning models for size and fit prediction.

The Biden administration is racing to rebuild senior agency roles depleted by the previous president, hiring at the fastest rate in decades, a POLITICO analysis found.

Higher inflation is riling up consumers and their lawmakers, but many economists say price increases will moderate soon. To investigate, we decomposed July’s inflation rate into its components.

To examine what makes UC Berkeley unique, The Daily Californian investigated the paths that UC Berkeley students take after graduation and the impact that college has on their careers.

First place, Best Multimedia Package, 2021 California College Media Association Awards