WONSEUK HER
Ossining,NY
Summary
Data Scientist with knowledge in handling large volumes of data of various nature and structure. Adept at communicating and acquiring domain knowledge to translate problems into actionable plans. Having a unique background, allowing analysis from various angles.
Overview
5
5
years of professional experience
Work History
Genetic Data Analyst
HistoGenetics LLC
11.2023 - Current
- Designed and implemented scalable algorithms for anomaly detection in genetic data, handling over 300k samples weekly and detecting novel allele patterns
- Created robust data pipeline to aggregate gene sequence data from multiple sources, standardizing its structure to drive actionable insights during weekly management meetings
- Developed and implemented 3 interactive dashboards and data visualizations for company-wide weekly meetings with 20+ participants, facilitating data-driven decision-making processes by communicating key performance metrics.
Research Intern
DAERYOOK & AJU LLC
05.2020 - 07.2020
- Orchestrated translation of 100 + pages of legal documents to ideate research findings on most-apt guidelines for efficient shipments across stakeholders’ trade
- Conducted extensive case law review to address product resale issue, formulating counter strategy for closure of arbitrage
Business Development Intern
SUNDOSOFT
06.2019 - 08.2019
- Partnered with marketing and business development teams to identify and pursue new applications of Geographic Information Systems (GIS) for precise data acquisition utilizing drone and satellite surveillance
- Streamlined data pipeline that retrieves data from credit card history and categorize according to its usage, achieving swifter reimbursement process of 50 + expenses per month for 10 + employees.
Education
Master of Science - Applied Data Science
University of Southern California
Los Angeles, CA05.2023
Bachelor of Science - Economics And Data Science
University of Southern California
Los Angeles, CA05.2023
Skills
- Python
- SQL (MySQL/MSSQL)
- Data Modeling
- PySpark
- Machine Learning
- Data Visualization
- Data Mining
- Cloud Computing
- English (native)
- Korean (native)
- Japanese (native)
Projects
- Apriori: Deciphered 522k rows of purchase data using Apriori algorithm, identifying over 260 recurring purchase patterns with single minute of compile time to potentially increase future revenue
- Recommendation System: Achieved scalable recommendation system that forecasts 142k customer rating of new businesses with RMSE score of 0.98 by combining traditional approach and ML techniques
- Sentiment Analysis using an LSTM model (NLP): Centralized existing model’s performance by employing LSTM model, resulting in 20% accuracy increase for discerning text’s sentiment
Timeline
Genetic Data Analyst
HistoGenetics LLC
11.2023 - Current
Research Intern
DAERYOOK & AJU LLC
05.2020 - 07.2020
Business Development Intern
SUNDOSOFT
06.2019 - 08.2019
Master of Science - Applied Data Science
University of Southern California
Bachelor of Science - Economics And Data Science
University of Southern California
Similar Profiles
SENTHILKUMAR NATARAJANSENTHILKUMAR NATARAJAN
Software Development Engineer at HistoGenetics LLCSoftware Development Engineer at HistoGenetics LLC
Sabrena LangstonSabrena Langston
Self Employed Owner/Operator at Bree'z Triple Care Transport, LLC/EAYC, LLCSelf Employed Owner/Operator at Bree'z Triple Care Transport, LLC/EAYC, LLC
David BondarchukDavid Bondarchuk
OTR Truck Driver at Kalinka Transport LLC/Bond Logistics LLCOTR Truck Driver at Kalinka Transport LLC/Bond Logistics LLC
Justin ChuchucaJustin Chuchuca
Mechanic at Mechanical EngineeringMechanic at Mechanical Engineering
Andrea RyanAndrea Ryan
Home Health Aide at FirstLight Home CareHome Health Aide at FirstLight Home Care