Hi, I am David

Inquisitive, passionate learner with an Economics background. Currently working towards a Master of Science in Statistics in NTHU.

Contact Me

About Me

My introduction

A skilled R and Python programmer who excels in the art of leadership. Equipped with a strong basis in math, programming logic, and data analysis framework. Current research is focus on spatial statistics and uncertainty of deep learning model, specifically, conformal prediction framework with spatial prediction.

02+ Years
experience
10+ Completed
projects
Download CV

Skills

My technical level

Programming

Python

90%

R

90%

C/C++

60%

SQL

70%

HTML/CSS

50%

Software & Tools

Hadoop

60%

Spark

70%

Git

70%

Docker

50%

Restful API

60%

AWS

50%

Frameworks

Tensorflow

80%

Scikit-Learn & caret

90%

Flask & Plumber

70%

tidyr & dplyr

90%

ggplot2 & Plotly

90%

Shiny & Dash

80%

OpenCV

60%

Qualification

My personal journey
Education
Experience

Master of Science in Statistics

National Tsinghua Univeristy
2020 - 2022
More Detail

Current GPA: 4

Relevant Coursework

  • Mathematical Statistics

  • Linear Models

  • Statistical Learning

  • Statistical Computing

  • Applied Multivariate Statistics

  • Time Series Analysis

Bachelor of Science in Economics

National Taipei Univeristy
2015 - 2020
More Detail

Overall GPA: 3.5

Last 60 credits GPA: 3.9

Relevant Coursework

  • Object-oriented Programming

  • Data Structures & Algorithms

  • Database System

  • Regression & Categorical Data Analysis

  • Longitudinal Data Analysis

  • Machine Learning

  • Multivariate Statistics

Data Analyst

Wistron Neweb Corporation, Internship
2021/07 - 2021/08
More Detail

Interactive Repair Data Analysis

  • Found potential factors that cause product anomalies in assemble and test procedure across two stages of manufacturing process

  • Constructed the pipeline of streaming and analyzing data to generate consistent quantitative based insight

  • Processed multiple tables of structural data from Oracle and Hadoop databases through SQL, Apache Phoenix and Spark (2GB+ per user request)

  • Developed a R-and-Shiny based web application with a dashboard to provide concise insights for other departments

Capstone Project

Legal Aid Foundation of Taiwan
2020/01 - 2020/07
More Detail

Investigation of Legal Aid Cases' Geographical Distribution and Significant Factors

  • Identified significant factors affecting the geographical distribution of legal aid cases

  • Improved the Foundation’s policy on prioritizing key areas and marked outlier regions, assisted the Foundation finding areas that are in urgent need for legal aid services or resource reallocation

  • Utilized Bayesian hierarchical model with spatial structure, modeled by conditional autoregressive model

  • Organized tasks for the technical team, comprised of four students, and cross-discipline communication with a researcher, an IT, and a specialist assigned from LAF

  • Won 1st place in National Taipei University Annual Statistic project contest

Research Assistant

National Taiwan University of Science and Technology, ME.
2020/11 - 2020/12
More Detail

Color Detection Web Application

  • Based on sensor imagery, calculate the designated proportions for various colors and further derive the volume of interest within a confined tubular space

  • Implemented with Python and OpenCV

  • Built a web application by using Restful API with Flask, Apache HTTP server, and deployed it on AWS EC2

  • Automation of modeling procedure for flow in convergent divergent nozzle

Research Assistant

National Taipei Univeristy, ECON.
2020/3 - 2022/8
More Detail

Double/Debiased Machine Learning

  • Conducted research in the areas of causual inference and machine learning, specifically, double/debiased machine learning

  • Constructed reports and weekly discussions on methods and simulation study with the professor

  • Reproduced the simulation results of papers of interest using R and Python code

Selected Projects

Most recent work

Variational Autoencoder - Face Generator

Auto-Encoder, Variational Inference

Built Variational Auto-Encoder (VAE) and Deep Feature Consistent VAE (DFC-VAE) for a face generator and facial attribute manipulation.

Rossmann Store Sale 48-days Prediction

SARIMA, Dynamic Regression

Utilized time series models to predict the sales of all Rossmann store after 48 days.

Spatial distribution of house price

Kriging, Spatial Visualization

Utilized statistical models to interpolate house price in Keelung-Taipei metro area.

IBM HR Analytics Employee Attrition and Performance

Machine Learning techniques

Utilized machine learning methods to model staff attrition: Naive Bayes, Logistic regression model, random forest, XGBoost and Bagging.

Effect of beta-carotene towards non-melanoma skin cancer

Longitudinal Data Aanlysis, GLMM

Utilized generalized linear mixed effect model to quantify the effect of beta-carotene towards non-melanoma skin cancer.

Text analysis for customer support on Twitter

Python, NLTK, gensim

Applied maximum likelihood methods to create smart word clouds for positive, neutral and negative twitters, and Built Latent Dirichlet Allocation model to discovery the topics of each twitter.



Contact Me

Get in touch

Call Me

(+886) 966-288-439

Email

davidlinn89222@gmail.com

Location

Hsinchu & New Taipei, Taiwan