About

Henoch Wong is a highly experienced Fraud & Abuse Machine Learning Engineer at LinkedIn with over 7 years of experience in designing experiments, developing software, and statistical analysis to interpret data. He is passionate about weaving together a narrative that leads to informed decisions and finding stories with a twist. Currently, Henoch is working on the multinational Daya Bay experiment of 200+ collaborators to make statistically significant discoveries using one of the world's largest neutrino datasets. He has written Monte-Carlo simulations, covariance matrices, and maximum likelihood estimators in C++ and Python that are used within the collaborations. His high precision measurement and search for new phenomena have led to 2 publications in high-impact physics journals. Henoch has worked as a Senior Data Scientist at c3.ai, where he worked on fraud detection for energy utilities, yield optimization for manufacturing, and supply chain inventory optimization. He has also worked as an Insight Data Science Fellow, where he created a Python-based web application to predict delays for BART and trained a machine learning algorithm to predict the likelihood that the delay time will change using Random Forest Classifier in Scikit-Learn, achieving a cross-validated accuracy of 87%. Henoch has a Master's degree in Experimental Particle Physics from the University of California, Berkeley, a Master of Mathematics in Theoretical Physics and Applied Mathematics, and a Bachelor of Arts in Physics from the University of Cambridge. He is highly skilled in ML, Python, Data Scientist, Search, Research Scientist, Random Forest, Web, Scikit, Flask, and Frontend. Henoch has 8.87 years of relevant experience and is enthusiastic about searching for new ideas hiding within interesting datasets. He can be reached at henoch.wong@berkeley.edu.