Staff Product Manager. Experience in social media, gaming, and live streaming; background in data analytics.

github

adplist

Andrea Boonyarungsrit  • Peerlist

Co-developed a three-stage human–AI pipeline to define, label, and deploy prosocial behavior classifiers where no established ground truth existed. Introduced a human-LLM disagreement loop to refine definitions and improve label quality, then deployed a two-tier inference system that cut inference costs by ~70% while maintaining high precision (~0.90). Demonstrated how deployment-aware ML design can unlock new responsible AI system capabilities at platform scale. Authors: Rafal Kocielnik, Min Kim, Penphob (Andrea) Boonyarungsrit, Fereshteh Soltani, Deshawn Sambrano, Animashree Anandkumar, R. Michael Alvarez

Prosocial Behavior Detection in Player Game C

Co-developed the first automated system to detect and classify prosocial behavior in in-game text chat at scale. Led product direction for a novel self-anchored attention model that improved classification accuracy by ~8% in low-data environments. Enabled platforms to move beyond disruptive behavior detection toward identifying, measuring, and reinforcing positive user interactions. Applied in production-adjacent research on Call of Duty with millions of DAUs. Authors: Zhuofang Li, Rafal Kocielnik, Fereshteh Soltani, Penphob (Andrea) Boonyarungsrit, Animashree Anandkumar, R. Michael Alvarez

Self-Anchored Attention Model for Sample-Effi

The Leadership Certificate Portfolio, part of the Illinois Leadership Certificate Program at the University of Illinois at Urbana-Champaign (UIUC), is the culmination of the Program, which details my leadership journey at UIUC. It includes I-Programs - half-day seminars to learn specific leadership skill sets in a dynamic setting, leadership programming - involvement in 10 hours of leadership programs on or off campus, and involvement in non-classroom team experiences.

Leadership Certificate Portfolio

Received the second place award at HackCulture 2019, an interdisciplinary hackathon that encourages collaboration across various UIUC majors. Working with four team members, the project's objective was to assess the credibility of cryptocurrencies using statistical methods to investigate potential relationships and correlations between select economic indicators, and addresses if cryptocurrency values correlate with the global economy.

The proposed hypothesis was that a currency’s credibility can be scored by how well its’ value correlates with select economic indicators. The degree of correlation can be used to determine its’ possible use case and financial strength in the global economy.

To assess the credibility of cryptocurrencies, regression analyses were completed using Microsoft Excel and correlation and clustering analyses were completed using R.