CakeResume 找人才
最轻量、快速的招募方案，数百家企业的选择
搜寻简历，主动联系求职者，提升招募效率。
- 浏览所有搜寻结果
- 每日可无限次数开启陌生对话
- 搜尋僅開放付費企業檢視的简历
- 检视使用者信箱 & 电话
职场能力评价定义
陳立峰 Li-Fong Chen
BS : NCTU/Applied Chemitry/2012-2016
MS : NCTU/Biology/2016-2018
Email: [email protected]
Primary skills
- Machine learning
- NLP
- Crawler
- Time series
- Proficient in python
Secondary skills
- Language : Javascript, Golang
- DB : MySQL, MongoDB, redis
- Cloud : GCP, AWS
- English
Experience
Wistron ITS
Project data scientist
2022/11/01 - present
Taipei, Taiwan
On-site Data Scientist at Dentsu
Custom Recommendation System - Two Tower Model: Developed a customized Two Tower recommendation model to enhance the accuracy and user experience of the recommendation system.
Optimizing Recommendation System - DeepFM Model: Modified and retrained the DeepFM model, significantly improving model performance through detailed adjustments and data analysis.
Reorganizing Data Pipeline on Google Cloud Platform: Optimized data processing workflows on Google Cloud Platform to enhance data processing efficiency and reliability.
Developing Text Mining Algorithms: Implemented new word discovery, word segmentation cleaning, TextRank, and other text mining technologies to support business needs and data analysis.
Language Model and Word Embedding Applications: Utilized tools such as CKIP, fastText, Word2Vec, and DeepCTR for sentence decomposition and analysis.
Remote Crawler Engineer
Python Crawlers: Responsible for designing and optimizing crawler strategies to improve data crawling efficiency and quality.
Database Management: Managed MySQL and MongoDB databases, ensuring data integrity and reliability.
Maintaining Asynchronous Golang API: Accountable for the maintenance of Golang APIs to boost system performance.
Other
Designed and developed a system for academic paper comparison.
DeepAR Model and Timeseries Data Processing: Engaged in projects involving the DeepAR model and processing of time series data.
FamilyMart
Data engineer
2021/06/15 -2022/10/05
Taipei, Taiwan
Applying Algorithms for Time Series Analysis: Utilized Generalized Additive Models (GAM) and AutoRegressive Integrated Moving Average (ARIMA) models for time series analysis to forecast inventory needs and sales trends for each store.
Multi-Model Classification Application: Set up an automated product labeling system using various classification models (XGBoost, Random Forest, etc.), comparing the performance of each to automatically select the most suitable model for product tagging.
Participation in Recommendation System Algorithm Development: Contributed to the development of recommendation system algorithms to enhance the accuracy and user experience of the recommendation system.
AWS Cloud Service Management:
- Automated ETL Processes: Utilized Amazon SageMaker to automate the Extraction, Transformation, and Loading (ETL) processes for recommendation system data.
- Virtual Machine Management: Responsible for the management of virtual machines on AWS, including configuration, monitoring, and maintenance, to ensure stable system operation.
Training and Awrads
Data competition champion
陳立峰 Li-Fong Chen
BS : NCTU/Applied Chemitry/2012-2016
MS : NCTU/Biology/2016-2018
Email: [email protected]
Primary skills
- Machine learning
- NLP
- Crawler
- Time series
- Proficient in python
Secondary skills
- Language : Javascript, Golang
- DB : MySQL, MongoDB, redis
- Cloud : GCP, AWS
- English
Experience
Wistron ITS
Project data scientist
2022/11/01 - present
Taipei, Taiwan
On-site Data Scientist at Dentsu
Custom Recommendation System - Two Tower Model: Developed a customized Two Tower recommendation model to enhance the accuracy and user experience of the recommendation system.
Optimizing Recommendation System - DeepFM Model: Modified and retrained the DeepFM model, significantly improving model performance through detailed adjustments and data analysis.
Reorganizing Data Pipeline on Google Cloud Platform: Optimized data processing workflows on Google Cloud Platform to enhance data processing efficiency and reliability.
Developing Text Mining Algorithms: Implemented new word discovery, word segmentation cleaning, TextRank, and other text mining technologies to support business needs and data analysis.
Language Model and Word Embedding Applications: Utilized tools such as CKIP, fastText, Word2Vec, and DeepCTR for sentence decomposition and analysis.
Remote Crawler Engineer
Python Crawlers: Responsible for designing and optimizing crawler strategies to improve data crawling efficiency and quality.
Database Management: Managed MySQL and MongoDB databases, ensuring data integrity and reliability.
Maintaining Asynchronous Golang API: Accountable for the maintenance of Golang APIs to boost system performance.
Other
Designed and developed a system for academic paper comparison.
DeepAR Model and Timeseries Data Processing: Engaged in projects involving the DeepAR model and processing of time series data.
FamilyMart
Data engineer
2021/06/15 -2022/10/05
Taipei, Taiwan
Applying Algorithms for Time Series Analysis: Utilized Generalized Additive Models (GAM) and AutoRegressive Integrated Moving Average (ARIMA) models for time series analysis to forecast inventory needs and sales trends for each store.
Multi-Model Classification Application: Set up an automated product labeling system using various classification models (XGBoost, Random Forest, etc.), comparing the performance of each to automatically select the most suitable model for product tagging.
Participation in Recommendation System Algorithm Development: Contributed to the development of recommendation system algorithms to enhance the accuracy and user experience of the recommendation system.
AWS Cloud Service Management:
- Automated ETL Processes: Utilized Amazon SageMaker to automate the Extraction, Transformation, and Loading (ETL) processes for recommendation system data.
- Virtual Machine Management: Responsible for the management of virtual machines on AWS, including configuration, monitoring, and maintenance, to ensure stable system operation.
Training and Awrads
Data competition champion