I am Sabrina, a Health Informatics, Statistics and Information Science major data enthusiast.
As a creative self-starter and passionate fast-learner, I am highly dedicated to developing data-driven insights, strategies, and solutions for companies and researches. I am interested in a data science, data analytics career within healthcare, tech, and business industries.
Please take a look at my portfolio and feel free to reach out if you have questions regarding to my past projects.
First Prize, Second Prize, 23rd International ICT Innovative Services Awards— Open Data, ICT Application
Python, R, SQL, Java, C++
Data Science and Machine Learning: Pandas, Numpy, Scikit-Learn, Spark, PyTorch Natural Language Processing: NLTK, Gensim, Topic Models (LDA)
HTML, Javascript, Django, GeoJson
MySQL, DB2, Neo4j
Microsoft (including VBA in Excel), VScode, Anaconda, GitHub, WEKA
With great interest in technology and programming, I have been dedicated in exposing myself to multiple tools and developing my skills in various programming languages. I have highlighted some of them below which I am most proficient in.
Key Courses:Computational Methods for Informatics, Computational Tools for Data Science, Applied Data Mining and Machine Learning, Topics in Deep Learning, Clinical Database Management Systems
Proficiency/Modules: Marketing Analysis, Data Management & Decision, and Big Data Industrial Intelligence Program.
Honors: Research Project Contest Excellence Award, Taipei Chung Cheng Scholarship, Academic Excellence.
• Applied data science techniques on quality and labor productivity producrts.
• Designed and developed systems to provide solutions and support manufacturing processes.
• Analyzed large-scale Uber’s drivers’ data, performed Latent Dirichlet Allocation (LDA) topic modeling on Zappos’ product reviews, and manipulated the Chain Store Guide (CSG) database through R and Python programming.
• Supported on a prosocial behavior change research paper by exploring, analyzing data and building probit models.
• Accomplished precision marketing for a health product startup through K-means clustering analysis and Light Gradient Boost Model (LGBM), which targets 80% potential customers using 16% of the list of people.
• Conducted data ETL through web crawler to support the company’s own Health Information System (HIS).
• Organized the data architecture and supported the foundation of the company’s Clinic Location Selection System product by creating data pipeline scripts to catch and preprocess updated data.
• Supported on an artificial intelligence Alzheimer’s disease (AD) prediction project and applied logistic regression on neuropsychological and neuroimage datum to further postpone the period of AD onset effectively.
• Participated in the development of Didi’s own analytics services by researching Google Analytics, Facebook Analytics etc. and interpreted the flow of products via these tools.
• Compiled the database, with the use of Hadoop Hive and having approximately 2,000 colleagues accessing each day, for the International Sales team by writing metadata in English, which supported in developing its market in South America.
• Business Development: Provided English demo lessons online for potential clients from Asia and effectively converted them to online course purchase. (Average rating by clients: 9.8/10)
• Evaluated clients’ performance and provide progress reports and learning advice.
Master of Science, Health Informatics
Bachelor of Business Administration, Statistics and Information Science
