Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I am Sherry, a data scientist with four years of experience delivering end-to-end data science projects, from concept to deployment, while managing stakeholder expectations. I specialise in publication-quality statistical analysis, visualization, NLP, time-series data processing, and deep learning, and I enjoy turning complex data into actionable business insights. I’m currently pursuing a PhD at QIMR Berghofer Institute of Medical Research in Australia, where I apply deep learning to wearable-device time-series data for chronic disease prediction and build scalable data pipelines on Google Cloud. I thrive on building modular, production-ready data analytics pipelines and bridging research with practical applications.…I am Sherry, a data scientist with four years of experience delivering end-to-end data science projects, from concept to deployment, while managing stakeholder expectations. I specialise in publication-quality statistical analysis, visualization, NLP, time-series data processing, and deep learning, and I enjoy turning complex data into actionable business insights. I’m currently pursuing a PhD at QIMR Berghofer Institute of Medical Research in Australia, where I apply deep learning to wearable-device time-series data for chronic disease prediction and build scalable data pipelines on Google Cloud. I thrive on building modular, production-ready data analytics pipelines and bridging research with practical applications.

Sherry Huang





I am Sherry, a data scientist with four years of experience delivering end-to-end data science projects, from concept to deployment, while managing stakeholder expectations. I specialise in publication-quality statistical analysis, visualization, NLP, time-series data processing, and deep learning, and I enjoy turning complex data into actionable business insights. I’m currently pursuing a PhD at QIMR Berghofer Institute of Medical Research in Australia, where I apply deep learning to wearable-device time-series data for chronic disease prediction and build scalable data pipelines on Google Cloud. I thrive on building modular, production-ready data analytics pipelines and bridging research with practical applications.…I am Sherry, a data scientist with four years of experience delivering end-to-end data science projects, from concept to deployment, while managing stakeholder expectations. I specialise in publication-quality statistical analysis, visualization, NLP, time-series data processing, and deep learning, and I enjoy turning complex data into actionable business insights. I’m currently pursuing a PhD at QIMR Berghofer Institute of Medical Research in Australia, where I apply deep learning to wearable-device time-series data for chronic disease prediction and build scalable data pipelines on Google Cloud. I thrive on building modular, production-ready data analytics pipelines and bridging research with practical applications.

Available to hire

I am Sherry, a data scientist with four years of experience delivering end-to-end data science projects, from concept to deployment, while managing stakeholder expectations. I specialise in publication-quality statistical analysis, visualization, NLP, time-series data processing, and deep learning, and I enjoy turning complex data into actionable business insights.

I’m currently pursuing a PhD at QIMR Berghofer Institute of Medical Research in Australia, where I apply deep learning to wearable-device time-series data for chronic disease prediction and build scalable data pipelines on Google Cloud. I thrive on building modular, production-ready data analytics pipelines and bridging research with practical applications.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Japanese

Advanced

Work Experience

PhD Student at QIMR Berghofer Institute of Medical Research

January 1, 2024 - Present

Apply deep learning models on time series data from digital wearable device (sleep, activity) for chronic disease prediction. Build data pipelines on Google Cloud using workflow tools.

Data Scientist at Chubb (APAC office)

December 1, 2023 - January 1, 2024

Led end-to-end data science projects from conception to deployment; engaged stakeholders to understand business needs to build models that drive business impact. Built classification models to detect subrogation opportunities using claims data with over 90% precision and ~30% actual conversion rate. Independently built reusable modular end-to-end data science pipelines using Kedro framework and deployed project on Databricks cluster. Designed and developed reusable NLP pipeline to extract features from unstructured claim documents utilizing vector embedding, RAG and hybrid search. Led the development of analytical python library for reusable data cleaning and transformation functions within the analytics team.

Data Scientist II (Real World Evidence) at Holmusk Singapore

November 1, 2021 - August 1, 2023

Design and execution of real-world data research projects. Designed and implemented modular, production-ready data analytics pipelines in Python. Characterized mental health patients and analyzed patient outcomes using statistical and machine learning techniques such as statistical tests, inferential models, clustering etc. Research and leadership: Initiated and led two real-world data research projects published at ISPOR conference. Promoted from data scientist I to data scientist II within 1 year. Big data engineering & Analytics: Designed and implemented data pipelines on AWS EMR clusters using PySpark for medical claims data (> 40 billion rows, > 200 columns ).

Data Scientist at Holmusk Singapore

November 1, 2023 - November 30, 2023

Part of Real World Evidence team focusing on data analytics pipelines, patient outcomes analysis, and leadership in project delivery.

Data Scientist at Chubb (APAC office), Singapore

December 1, 2023 - January 1, 2024

Led end-to-end data science projects from conception to deployment; engaged stakeholders to understand business needs to build models that drive business impact: Built classification models to detect subrogation opportunities using claims data with over 90% precision and ~30% actual conversion rate. Independently built reusable modular end-to-end data science pipelines using Kedro framework and deployed project on Databricks cluster. Designed and developed reusable NLP pipeline to extract features from unstructured claim documents utilizing vector embedding, RAG and hybrid search. Led the development of analytical python library for reusable data cleaning and transformation functions within the analytics team.