張維庭 William Chang
Have 5+ years experience in Data Analysis
Expertise in the areas of machine learning, data visualization, and NLP
Data scientist, Data engineer, Data analyst, AI engineer
Taichung，TW
[email protected]
TECHNICAL SKILL
Software/Platform
- Hadoop, MySQL, MongoDB
- Git, Docker
- SAS, MATLAB
- PowerPoint, Excel, Word
Programming
- Python, C/C++, R
- SQL,
- D3.js, CSS, HTML
- Swift
Operating Systems
- Windows
- MacOS
- Linux
DATA ANALYTICS and DATA SCIENCE EXPERIENCES
Information Retrieval & Web Search, UCR
Recipe Search Engine Jan. 2020 – Mar. 2020
- Collected data form the website (Allrecipes) using Scrapy and stored them by Hadoop.
- Built index for search engine through two methods. The first used PyLucene with assigned filed, and the second created pipeline to calculate TF-IDF on Hadoop.
Big-Data Management, UCR
Twitter Data Analyze in Car Brand Topic Sep. 2019 – Dec.2019
- Crawled the text contents related to car brands through Scrapy and stored them into MongoDB.
- Created multiple processes to generate key word and brand popularity analytic results.
- Visualized the results into interactive graph such as word cloud and geographic hotspot map and built a webpage to support all the search queries by python Dash.
Research Assistant, Machine Intelligence Group (MIG), NCCU
Automated word segmentation in Tang poetry and epitaph project Jun. 2019 – Jul. 2019
- Implemented an analyze tool to verify quality of data labeled by different source
- Trained word embedding model via gensim word2vec package
- Combined word embedding model with LSTM model (Keras) and added some special feature (e.g. rhyme) to implement an auto procedure to fulfill word segmentation in poetry and epitaph
- Improved the model precision to near 90% and presented the result in short paper and was
successfully accepted to Digital Humanities 2020 Conference
Research Assistant, Machine Intelligence Group (MIG), NCCU
Chinese text content simplification and compression project Nov. 2018 – Dec. 2018
- Used python beautiful soup package and regular expression operations to extract contents collected from Biographies in Local Gazetteers
- Designed a syntactic analytic application which could generate simplified and compressed Chinese text content by combining python NLTK package and Stanford NLP tool
- Demonstrated the application result of content simplification and compression in short paper and was
successfully accepted to Digital Humanities 2019 Conference
Undergraduate special topic on computer science, NCCU
HiCmapTools: A tool to analyze Hi-Contact Data Jul. 2017 – Feb. 2018
- Designed a set of computation procedure tools by C++ to help biologist perform data analysis on different queries
- Fulfilled an auxiliary statistic tool (R) to visualize result and analyze the quality
- Received a research grant from Academia Sinica (project number: 106-2813-C-004-036-E )
- Won third place in department exhibition
EDUCATION
University of California, Riverside, Riverside, CA (UCR) Dec. 2020
Master of Science in Computer Science
- Relevant course work:
Big-Data Management, Artificial Intelligence, Information Retrieval and Web Search, Probability Model for Artificial Intelligence, Data Mining Techniques, Statistic, Database System, Information Visualization, Business Analytics with SAS/R
National Chengchi University, Taipei, Taiwan (NCCU) June 2018
Bachelor of Science in Computer Science
- Completion of Big Data Analytics Program for Undergraduates
- Certificate in Fintech
HONOR
- Academic Excellence Award, NCCU Feb. 2018 – Jun. 2018
