Ian Herve Chu Te
Data Scientist / Machine Learning Engineer / Full-stack Software Engineer
Website Kaggle LinkedIn GitHub StackOverflow Acclaim EXPERIENCE
Golden Entropy Marketing — Data Scientist
Los Angeles, CA (remote) October 2022 - present
● Various loan lead valuation and optimization models and algorithms Bodhala — Machine Learning Engineer
NYC, NY / Ann Arbor, MI (remote) March 2021 - October 2022
● Various legal spend-related use cases (confidential) Star Media Group — Data Scientist, Manager
Kuala Lumpur, Malaysia August 2019 - August 2021
● Weekly Summary Generator with automated summarization of articles, intelligent topic grouping and selection (sample)
● Propensity models for subscription, free trial and churn
● Methodologies for building optimized audience segments
● News article taxonomy tagger enriched by metadata from WikiData and locally-curated entities and topics
● Content attribution model using Shapley values
● Automated calorie and cooking time estimation algorithm
● Several web scrapers for competitor analysis
(Python, Pandas, Scikit-Learn, Keras, TensorFlow, Google Compute Engine) SEEK — Data Scientist
Kuala Lumpur, Malaysia December 2018 - March 2019
● Automated, context-sensitive business entity fingerprinting engine (for lookalike search, mining of “human-like” latent variables, topic prediction)
(Python, Pandas, Spark, Scikit-Learn, Keras, PyTorch, TensorFlow, Databricks) Astro — Senior Associate, Data Scientist
Kuala Lumpur, Malaysia October 2017 - October 2018
● Unsupervised, automated football match highlights generator (from video and audio features)
● TV subscription propensity-to-purchase model based on historical subscription, viewership and interactions data
● Customer value model that forecasts the future 1-year value of a customer
● Custom address matching algorithm optimized for Malaysian addresses
(Python, Spark, Scikit-Learn, XGBoost, Keras, PyTorch, TensorFlow, Docker) Teradata — Data Scientist
Metro Manila, Philippines September 2016 - June 2017
● Several data analytics proof-of-concept projects (market basket analysis, text tagging, text classification, image classification and audience targeting) Email:
ad2vfh@r.postjobfree.com
AWARDS
Data Unchained Malaysia 2018 -
1st place (team)
Data Unchained Malaysia 2018 -
Best Data Scientist (individual)
AWS Hackdays: ML Malaysia -
1st place (team)
AWS Hackdays: ML Southeast
Asia - 3rd place (team)
Cum Laude (GPA 3.4)
Lexmark Corporate Scholar
CERTIFICATIONS
IBM Data Science Professional
Certificate
Teradata Aster Professional
Hortonworks Certified Associate
TOEFL
Programming in C#.NET
PSM 1 Certified - scrum.org
LANGUAGES
Native:
● English
● Filipino
Tagalog
Bisaya
Basic:
● Bahasa Malaysia
● Chinese (普通话)
● Reusable machine learning plugins in the Dataiku platform
(Teradata, Aster, Dataiku, Python, Spark, Scikit-Learn, TensorFlow) BCV Evolve Social (Part-time) — Data Engineer
Chicago, USA (remote) March 2016 - September 2016 ETL scraper tool for TripAdvisor data; real-time dashboards
(Clojure, PostgreSQL, Enlive)
Code Ninja — Software Engineer
Metro Manila, Philippines March 2016 - September 2016 Real-time analytics dashboards
(PHP, JavaScript, Firebase, PostgreSQL)
Accenture — Software Engineer
Cebu City, Philippines January 2015 - March 2016 Data-driven banking and media web applications
(C#.NET, JavaScript)
Lexmark — Software Engineer
Cebu City, Philippines May 2013 - December 2014
Interactive waveform tool for diagnosing printer mechanisms
(C#.NET, XNA Game Studio)
EDUCATION
Silliman University, Philippines — BS Computer Science Thesis: “Deep Learning Gaussian Radial Basis Function Networks with an Application to Phone Recognition” (published at IRCIEST 2013 - page 60) 2008 - 2013
Georgia Institute of Technology, USA — MS Computer Science Specialization: Machine Learning
2018 - 2022
PERSONAL PROJECTS
LambdaML — an extensible functional ML library for Python Shapley Attribution Model — Shapley Value for Attribution Zalora Scraper — a web scraper for Zalora written in Python chutychart.js — a stock visualization library for JavaScript toady — easily visualize high-dimensional data in 2d space Goalpost Detector — OpenCV-based goalpost detection algorithm ianchute-website — my personal website