Mina Ghashami

ghashami@amazon.comCVGoogle ScholarLinkedin

About me

I am an applied scientist in Alexa Video team at Amazon where I work on recommender systems.

Until September 2020, I was a research scientist at Visa Research; where I worked on numerous projects including “Transaction Predictor”; a graph neural network that predicts next transaction of cardholders and merchants, “Group recommender for Restaurants”; a deep neural network trained on individual’s transactions that recommends restaurants to a group of cardholders, and "cause analysis engine", an AI-based data driven system that provides merchants with actionable insights to improve dropped sales and reduce operating costs.

I received my PhD in Computer Science from University of Utah where I worked on matrix sketching techniques in data streams. After that, I was a Postdoctoral fellow at DIMACS, Rutgers University.

My research interests are recommender systems, scalable machine learning, streaming and online algorithms, matrix approximation and dimensionality reduction.

Past Interns

  • mahsa shafaei - University of Houston - 2020

  • Lan Wang - University of Illinois at Urbana-Champaign - 2019

  • Zhe Xu - University of Illinois at Urbana-Champaign - 2018

Academic Work

I have been on academic review committees for many conferences including KDD, DAMI Springer, SISC, STACS, and PC member of AISTATS, NIPS, ICML.

Teaching

Publications

Patents

  • Graph learning-based system with updated vectors

    with Fei Wang, Mahsa Shafaei, Hao Yang

  • Computer-implemented method, system and computer program product for group recommendation

    with Hao Yang, Hossein Hamooni