Projects

Here you’ll find a list of my research and applied projects😊.
If you’re interested in collaboration or want to know more details, please 📧contact me.

Research on Social Familiarity and Self in the Uncanny Valley: A Multidimensional Exploration (Master Thesis)

Author & Lead Researcher | Advisor: Prof. Guomei Zhou
Duration: Dec 2024 – Present

This project investigates the uncanny valley effect from the perspectives of social cognition and self-concept, focusing on emotional, cognitive, and social mechanisms. It also includes the development and validation of a new scale to measure human threat perception and defensive mechanisms toward robots.

Mapping Decision-Related Neural Dynamics Across the Mouse Brain Using Machine Learning Approaches

Lead Researcher | Neuromatch Academy - Computational Neuroscience
Duration: Jul 2025

Using open-access IBL data, this project applies machine learning to decode and map decision-related neural signals across the mouse brain.

Recency Effect in the Ensemble Perception of Average Facial Attractiveness

Author & Lead Researcher | Advisor: Prof. Guomei Zhou
Duration: Nov 2023 – Aug 2024

  • Explored how recent stimuli influence ensemble perception of group facial attractiveness
  • Designed and conducted four experiments using RSVP paradigms with morphed and real faces
  • Demonstrated that later-presented faces exert disproportionate weight on group attractiveness judgments
  • Established a weighted-processing model and linked the recency effect to memory constraints

User Mental Model Construction for 3D Virtual Fitting Room

Author & Researcher | Advisor: Associate Prof. Qi Wang
Duration: Apr 2024 – Jun 2024

  • Developed a preliminary user mental model for 3D virtual fitting room applications
  • Analyzed user needs, personas, and behavioral patterns in online apparel shopping
  • Designed user-centered functionalities and usability testing scenarios
  • Proposed solutions for optimizing shopping experience and reducing return rates

Bank Product Customer Subscription Prediction with LightGBM

Author & Researcher | Advisor: Associate Prof. Ying Lin
Duration: Oct 2024 – Jan 2025

  • Built a machine learning system for predicting customer subscription to bank products
  • Conducted comprehensive data preprocessing and feature engineering
  • Compared and optimized Decision Tree, Random Forest, XGBoost, and LightGBM models using Optuna
  • Performed model evaluation, stacking ensemble, and feature importance analysis
  • Delivered actionable recommendations for marketing strategies