Research & Projects

Independent Researcher

Global Healthcare Workforce Data Analysis - Extension:
This study provides more details in statistical analysis, utilizing simple linear regression and multiple linear regression for further analysis. This report can support the government in its public health planning. For example, from the results of statistical analysis, we highlight different trends in the availability of healthcare professionals in Australia, which is broadly in line with the 10-year plan developed by the Australian Government's National Health Workforce Strategy 2021-2031 plan (Australian Government Department of Health and Aged Care, 2023).

Global Healthcare Workforce Data Analysis:
Interactive global density maps, completed for the multivariate analysis session, present healthcare workforce trends and availability for 66 countries over a 13-year period. The dataset used in this study is extracted from the Global Healthcare Workforce Statistics database, maintained by the World Health Organization. My contributions to this study include data cleaning, development of interactive dashboards, and health policy research in selected countries. The detailed report contains the interpretation of trends in four types of healthcare professions in some countries, combined with relevant policy discussions in selected countries.

Research Collaborator

Regression and Bivariate Normality:
The regression and bivariate normality analysis, undertaken for Applied Multivariate Analysis course, analyzed the regression relationships between complaints variable and other variables in a hospital.

Sentiment Optimization on Social Networks:
Applying linear regression and stepwise selection to identify significant correlations between social media activity and emotional responses of users on Twitter.
My research work in social media analytics led to the publication of my first individual research paper “Analysis of Sentiment Optimization on Social Networks Based on Statistical Data” at the IEEE International Conference on Computer Science, Artificial Intelligence, and Electronic Engineering (CSAIEE).

ML Analytics for Predicting Future Stock Prices:
The project, undertaken for the capstone at Cornell and collaborated with Gravity Investments, focuses on analyzing the quality of trustworthiness and providing more reliable stock predictions to better support Gravity Investments to make informed decisions. We had weekly meetings to update our progress with our client and a poster which was presented at the end of the semester
The work includes database building, model analysis, and feature selection. My work focus on the model analysis to help our client to identify outliers by using squared return errors, the model realism with predicted return, the model performance using decile chart, and the correlation between predicted and actual returns.

Predicting the Quality of Wine:
The research project, completed for the Data Mining & Machine Learning course, analyzes the test accuracy of seven machine learning models, such as KNN, LDA, QDA, Logistic Regression, and Random Forest, on the prediction of wine quality.
I am responsible for analyzing LDA, QDA and logistic regression. In this study, QDA does not work due to dimensionality issues, while LDA and logistic regression have test accuracies of 53.54% and 50.60%, respectively, when using unbalanced training datasets.

HR Management Project: Understanding KSAOs:
An in-depth job position analysis including the design of situational/fit/behavioral interview questions and the comparison of KSAOs on O*Net , completed for Talent Acquisition course, identifies both alignments and discrepancies between real-work job demands and standardized occupational benchmarks.

Research Collaborator

Independent Researcher

Capstone Collaborator

Research Collaborator

Independent Researcher