Hai Bao

647-831-8623 | hbao12@gmail.com | hbao.ca

SUMMARY STATEMENT

Senior Data Scientist with proven expertise in integrating LLMs (like GPT) to optimize data harvesting, reducing daily article volume by 25%. Skilled in text mining, creating Python/Plotly monitoring dashboards, and achieving significant workload reduction for ESG analysts.

EXPERIENCE

Senior Data Scientist

Jan 2023- Present

Morningstar Sustainalytics, Toronto, ON

● Responsible for maintaining the News Harvester System, which is a system that imports 400,000+ articles daily and filters them out for ESG relevance for ESG Analyst review.

● Integrated LLM-based solution (GPT) into the News Harvester System to help filter the news articles more efficiently, which resulted in the reduction of articles daily by 25% (approximately 1000 less articles per day).

● Created a Plotly dashboard in Python to monitor daily metrics and assist with anomaly detection. The dashboard is consumed by stakeholders through a daily automated email.

● Evaluated model performance using scikit-learn.

Data Scientist

Nov 2021 - Jan 2023

Morningstar Sustainalytics, Toronto, ON

● Responsible for maintaining the Thematic Crawler (web/internal database crawler).

● Improved text mining performance of the crawler through use of multilayered keywords. Was able to reduce the number of hits by approximately 50%, effectively reducing workload for ESG Analysts in half.

Network Capacity Planner

Dec 2014 - Apr 2020

Zayo, Toronto, ON

● Responsible for identifying cost optimization opportunities through SQL queries of the network equipment inventory database.

● Transitioned opportunities into realizing cost savings through implementation of network engineering projects (node installations/decommissions, customer circuit migrations).

● Worked on a project to vacate 2 floors of a data center in order to realize $2 million dollars worth of cost savings.

EDUCATION & CERTIFICATIONS

Bachelor of Science, University of Toronto

Sep 2005 - Aug 2010

Statistics Specialist

Machine Learning , IBM

Sep 2021

Covered topics such as Regression, Classification, Deep Learning, Time Series, Unsupervised Machine Learning

Data Analytics , Google

Jul 2021

Covered topics such as Exploratory Data Analysis, Data Engineering, Data Cleaning, Creating Visualizations

Natural Language Processing, DeepLearning.AI

Dec 2021

Covered topics such as Sentiment Analysis, Part-of-speech Tags, Named Entity Recognition

Tableau Desktop Specialist, Tableau

Nov 2020

SKILLS

Python Programming

Data Analytics

Data Visualizations

Machine Learning Modelling (XGBoost, Random Forest, etc.)

GenAI/LLM Integrated Solutions

Github