陳宣佑 HsuanYu CHEN

From the background of statistics in NCCU, Yu graduated from his master degree in Institute of Service Science in NTHU, with a major module of business data analytics. He has 4 year experience of Python and R in his college projects and 6 internships, including chatbot, comdceputer vision, time series forecast, recommendation system, customer clustering / prediction, and NLP etc. His thesis focuses on improving literature review efficiency with semi-supervised learning on a small number of PDF data. Compared to normal CS background students, Yu not only has solid programming skills with statistical concepts but also great communication skills due to the previous bilingual learning environment when exchanging to Japan. 

Intern & Research Assistant

LINE, TECH FRESH  [R, Python, Hive, Spark, K8S]                                      Jul 2020 - Jun 2021

    -     Check raw data quality and source back to KR/JP data source to improve data quality

    -     EDA on large scale EC web record with pySpark, SQL to find insight

    -     Data visualization report & R dashboard with K8S

    -     Recommendation API service from scratch, including algorithm, ETL, API deployment, metrics

    -     Recommendation related metrics study, documentation from biz, model, UX aspects

CRUXOVER, Data Engineer  [Python, R, Azure]                                        Oct 2019 - Sep 2020

    -     Recommendation system with spark.ml

    -     Python & R tutorial design

    -     Potential Customer Prediction with data pipeline using Azure

    -     Refactor Python feature engineering code into SQL, saving 80% computation time

    -     IoT data engineering & code refactor

NTHU, Research Assistant of SDG project  [Python]                               Jun 2019 - Dec 2019

    -     Research various deep learning embedding technique in NLP 

    -     Web crawling of online journal paper

InQuartik, NLP Assistant Engineer (Summer Intern)  [Python]             Jul 2019 - Sep 2019

    -     Japanese English translation algorithm NLP research

Cinnamon, Computer Vision Researcher (Summer Intern)  [Python]  Jul 2019 - Sep 2019

    -     Build a web AI application which can classify over 100 categories of NIKE shoes

    -     Integrate front-end & model with python flask, numpy, pandas

    -     Design marketing plan and pitch this AI product to CEO

    -     Independent research of CV algorithm for better image segmentation performance

IProspect, Data Consultant/ Data Analyst [Python, R]                          Feb 2019 - Jun 2019

    -    Data cleaning & Feature engineering of large scale makeup shopping data 

    -    Applied Xgboost algorithm to predict probability of buying each category of makeup for each customer  

    -    Applied Cspade association algorithm to mine customer behavior and give recommendations to ad 

Gigabyte, Data Science Intern [Python]                                                  Aug 2018 - Jun 2019

    -     Build customer & inner-service chatbot from scratch

    -     Build automated program to produce daily recognition data analysis report with visualization.

    -     Linux OS Python environment building, Gitlab code version control

    -     App/ Software interface English/ Japanese translation

AIU, Japanese Learner Quantitative Research Statistics Assistant   Dec 2017 - Jul 2018

    -    R programming & Statistics Model Teaching

    -    Give advice of how to quantitatively analyze learners' result

Course Project

[Business Analytics with Time Series] - T. S. Prediction & Dashboard               Dec 2020

    -    Fit & select various time series model for explain & prediction purpose

    -    Build a dashboard with R of real-time prediction & customer statistics

[Business Analytics with Data Mining] - Video Platform Customer Tagging     Jun 2020

    -    Predict suitable plan for free user

    -    Predict user that may cancel in the next period based on behavior feature

[Text Mining] - NLP based Song Recommendation                                               Jun 2019

    -    Use Google Universal Sentence Encoding to recommend song with lyrics

[Side Project] - SET News WordCloud Chatbot                                                      Apr 2019

    -    Real time crawling of web data through user's query

    -    Build back-end system with cloud server Heroku and Python web framework "flask"

    -    Apply jieba package with pandas' vector computation to speed up reply time

[Big Data Analysis] - Gamer Shopping & Deposit Recommendation System   Dec 2018

    -    Data cleaning & Feature engineering of over 1,000,000 deposit, item shopping, login data

    -    Cluster user behavior with EM machine learning algorithm and make marketing plan for each group

    -    Build a recommendation system in Python to implement collaborative filtering (Test Accuracy: 90%).

         (It was build as a web application with Flask, HTML, Jinja. It can be as designed as a API for game system)

[Machine Learning] - Twitter Text Mining & Neural Network Emoji Predict     Jun 2018

    -    Stream over 30000 text data with Twitter API and process the text data

    -    Reduce dimension with t-SNE algorithm and plot the vector relation of emoji 

    -    Predict emoji based on text with bag-of word and DNN, Xgboost.

[Econometrics] - Mango Pricing Time Series Analysis [R]                                      Jun 2017

    -    Collect fruit transaction data from public platform and crawl historical weather data

    -    Statistics test on various time variable to find significant ones

    -    Write into statistics report of how pricing of mango can be forecasted by my model

[Psychology Digital Technics] - Dcard Web Crawler & Text Mining [R]                Jun 2017

    -    Stream articles data from different forum and data cleaning

    -    Visualize word using behavior for different gender with wordcloud

         (Males have more word about 'myself',, females have more word about "my boyfriends")


National Tsing Hua University, Service Science, Master                  Feb 2019 - Jun 2021

    -    Master degree of Service Science with major of information system & data analytics

    -    Course including quantitative and qualitative analysis method

Akita International University, Exchange Student                           Sep 2017 - Aug 2018

    -    Represent NCCU as exchange student, studying global business, machine learning, information science

    -    Language Exchange program as English, Chinese teacher

National Cheng Chi University, Statistics, Bachelor                       Sep 2014 - Jan 2019

    -    Course from basic to advance statistics, such as ANOVA, mathematical statistics.



Python: sklearn, tf, flask, pyspark,   jieba, gensim, etc

R: ggplot, dplyr, various statistics         model etc




    -    TOEIC 945 [2018/7]

    -    TOEFL 97 [2016/9]


    -    N1 152 / 180 [2018/7]

Online Course


    -    Natural Language Processing

    -    Sequence Model (deeplearning)

    -    Applied Machine Learning

    -    Bayesian Statistics 

Extracurricular Activities

NCCU Recruit Month [Annual Event],  Marketing member               Dec 2016 - Mar 2017

    -    Write Facebook Articles to promote each company to students

    -    Design virtual events to let students know more about the content about our event

    -    Collect questionnaires and visualize with  R's ggplot2.

NCCU Statistics Camp 7th, Marketing & Public Relation leader         Apr 2016 - Jul 2016

    -     Write Facebook Articles to promote the camp to high school student (Finally over 130 students enrolled)

    -     Track View data from Facebook backend to customize the article content

Powered by CakeResumePowered by CakeResume