libraries for predictive analysis of customer behavior. Designed and implemented a scalable data warehouse architecture using Apache Cassandra, PostgresDB, and Redis. Optimized database performance by tuning queries in SQL Server, Oracle and PostgreSQL databases. Implemented efficient data processing algorithms on large datasets with Apache Spark, MapReduce, and Pandas Python. Created dashboards in Tableau Desktop Professional Edition to visualize complex datasets in an interactive manner. Created custom scripts to automate the extraction, transformation, and loading of Big Data into distributed systems. Utilized Amazon Web Services components such as EMR and S3 buckets for cloud computing

宋浩茹 Hao-Ru Sung| [email protected] | LinkedIn ｜ GitHub A s a Research Assistant at Academia Sinica , specializing in Generative AI research and application. With 3 + years of experience in NLP a nd Machine Learning , along with 4+ years in Backend Development . Proficient at translating complex theories into practical applications. Skills Languages: Python, R, SQL, MATLAB, C, C#, JavaScript, Node.js Software & Tools: PyTorch, PyTorch Lightning, Tensorflow, Scikit-Learn, NLTK , GCP, Linux, SQL / NoSQ , Pandas, Hugging Face, Gradio, LangChain, Tensorflow, Keras, FastAPI, OpenCV, Airflow

Computing Library) : Numpy is one of the core libraries for numerical computing in Python. It provides powerful mathematical functions and array operations, capable of handling multidimensional arrays and matrix operations. In data processing and analysis, Numpy is an indispensable tool for efficiently handling large amounts of data. Pandas (Data Analysis Library) : Pandas is an important library in Python for data analysis and data processing. It offers powerful data structures such as DataFrame and Series, making data reading, manipulation, and analysis more convenient and efficient. Pandas is well-suited for tasks such a...

測模型 side project 使用深度學習框架(Pytorch)自行搭建預測模型，以各式台灣景氣指標當作輸入，輸出未來經濟景氣趨勢階段。 技術：Pytorch、Pandas、Numpy、 Sklearn 論文發表 • Chen, X. Z., Li, M. C. , & Chen, Y. L, January). Strategies for Helping Anchor-Based Trackers Learn re-ID Features for Smart City Surveillance. In 2024 IEEE International Conference on Consumer Electronics (ICCE) (ppIEEE. • Li

端工程師 緯創軟體 五月十月 2023Taipei, Taiwan 【Wafer Data Correlation專案】 比對晶圓同 product 不同批的 lot 或 wafer 間的關聯性 利用Python的 Sanic Framework 建置後端API 透過Pandas處理資料流 規劃 DB Table 間的Constraint和重構效率差之DML語法 【Defect Loader專案】 尋找 wafer 缺陷圖片＆搬運 利用Spring Boot建置 【Docker＆K8s】 1. 上述的專

programming was going to my Bachelor's degree, C++ was the first program I learned. Then I started to learn Python in 2018 at TEDU and my first project was the Stock Trend Prediction by CNN. I kept using Python to implement web crawling, OOP, and Pandas in my job, intend to let my work become more automated. I used those techniques to automate the data-gathering problem, which shorten the existing progress duration. I'm very passionate about Data Scientist and Machine Learning. Work Experience Product Manager • 東元電機股

Data Scientist Intern @ Cathay Financial Holdings. 國泰金控 Digital data & Technology (DDT, 數數發) Research into Interpretable Machine Learning and its existing algorithms. Experimented LIME & SHAP on open data. ( GitHub ) Real Estate Evaluation model – Geographical/Credit Card data gathering, cleaning, feature engineering (Hit-rate performance improved from 55% to 70%) Python Machine learning Data Pipelines Web Crawlers PyTorch, Airflow, Pandas, docker SQL Extract-Transform-Load(ETL) Efficiency(Window Functions) Language Chinese(Native) English (TOEIC 905/990 TOEFL 96/120) Project(@ Esun only) ( Powerpoint demo link, clic...