Wang Xinzhou

Education

06/2024 – 09/2025

Major: Data Science
Research Areas: Data Engineering and Artificial Intelligence
Core Courses:
- Data Engineering
- Artificial Intelligence and Deep Learning
- Data Pipelines and Stream Processing
- Time Series Analysis and Forecasting
- Analytical Systems Engineering
- Natural Language Processing
- Supervised/Unsupervised Learning Models
- Data Science and Cloud Computing
- Knowledge Engineering
- Applied Statistics
- Computer Vision

09/2020 – 06/2024

Major: Information Management and Information Systems
Minor: Business Administration
Core Courses (First Degree):
- Advanced Mathematics
- Linear Algebra
- Probability Theory and Mathematical Statistics
- Data Structures
- Programming
- Algorithm Design and Analysis
- System Design and Analysis
- Databases & Data Warehousing
- IT Project Management
- Machine Learning and Data Analysis
- Financial Programming
- Computer Networks
Core Courses (Second Degree):
- Economics
- Financial Accounting
- Managerial Accounting
- Financial Management
- Marketing
- Global Operations and Supply Chain Management
- Human Resource Management

Languages: C++, Python, Go, SQL, R
Frameworks & Libraries: Django, Nginx, UWSGI, Hugo, Pandas, Sklearn, PyTorch, TensorFlow, Pentaho Kettle Spoon, Unreal C++, Blueprints, Pygame, Excel VBA, HTML, CSS, JavaScript

12/2023 – 06/2024

Built and developed data-driven automated workflows and toolchains to improve analysis efficiency, promote customer engagement and retention.
- Player Sentiment Analysis
Daily Tasks:
- Managed, processed, and analyzed user data at the scale of tens of millions.
- Designed and developed web-based game data analysis tools.
- Built standard workflows and automation for weekly game data reports.
- Compiled comprehensive user research reports.
- Reported to the CEO’s business assistant.
Executed multiple special analysis tasks requested by senior management, including:
- Player game resource demand analysis
- Special weekly reports displaying key metrics (e.g., DAU, ARPU, LTV)
- Analysis of streamer advertising placements and revenue sharing
- Revenue and lifecycle forecasting for certain games.
Utilized database and data warehousing skills to design and develop structured data flows, constructing data integration tools and visual dashboards for a newly launched large-scale mobile game.
Designed and developed a reusable NLP system based on sentiment analysis to categorize and score player reviews using Django.

07/2023 – 09/2023

Developed and deployed a real-time monitoring system for user log data streams.
- Data Streaming Workflow
Participated in a large-scale software development project using Nginx log modules, Hadoop, Kafka, Flume, and Flink.
Utilized Elasticsearch for data visualization, reducing communication costs between customers and marketing experts through data visualization.

05/2023 – 07/2023

Led a student team to design and develop an AI intelligent voice assistant for a large tunnel construction site in Shanghai.
- ASR Project
Reviewed and evaluated modules for Automatic Speech Recognition (ASR) and Text-to-Speech (TTS).
Led the design, development, and integration of five software functional modules.
Conducted rigorous testing and deployed the system to a Linux Ubuntu server for production use.

04/2024 – 06/2024

Project: Polaris Note integrates an AI text completion tool using large language models and RAG-based text prediction.
- PolarisNote
Algorithm Level:
- Employed TF-IDF for pre-training document selection.
- Used Latent Dirichlet Allocation (LDA) to extract topic preferences.
- Built a private, searchable vector database for RAG using the WIKI Knowledge Base.
- Applied optimizations to address limitations of autoregressive models.
Web Application Development Level:
- Features include cookie-based user authentication, personal dashboard, AI-assisted note creation, Markdown support, note browsing, management, developer console, and application settings.
- Authored comprehensive documentation for Django, Nginx, UWSGI.
- Frontend built using HTML, CSS, and JavaScript.

12/2022 – Present

Hugo-Based Website:
- BellowAverage.github.io
- Direct URL: https://bellowaverage.github.io/
Old Django Site (No Longer Maintained):
- OldDjangoSite
- Developed with Django, Nginx, and UWSGI.
- Hosted many of my work’s APIs.

11/2022 – 12/2022

Project: MySQL-based database system for PC game distribution.
- GameDataWarehouse
Designed ER diagrams, performed normalization, and implemented the relational database system.
Established ETL data pipelines using Pentaho Kettle Spoon.
Implemented data visualization using Microsoft PowerBI.

10/2022 – 11/2022

Project: Machine learning-based workflow for visualizing and predicting taxi trajectories.
- TrajectoriesPrediction
Enabled extraction and EDA from Microsoft’s Geolife GPS V1.3 data.
Trained and evaluated supervised learning models including KNN, linear regression, SVM, random forests, and LSTM.
Participated in multiple Kaggle competitions such as Boston Housing, Titanic, MNIST, Cats vs Dogs, US Used Car Price Prediction, etc.

09/2021 – 02/2025

OrionUnrealFramework:
- OrionUnrealFramework
- Features a behavior queue system for AI logic and an extensible procedural AI action framework.
Python Shooting Game:
- PythonShootingGame
- Developed a 2D physics engine, collision detection, and 360-degree movement.
VBA RPG Game:
- VBAGame
- Designed game mechanics, in-game purchase systems, dynamic events, and backend data analysis framework.

07/2020 – 09/2022

Led a student volunteer team of over 30 members for two consecutive years.
Provided support for international student affairs, serving over 200 international students and foreign faculty and staff.
Coordinated and managed influential events promoting the university within the overseas community.

Second Prize (Twice: 2021 & 2023) | Shanghai University Academic Excellence Scholarship
Second Prize (National Finals) | 2021 IEERA China Business English Debate Competition
Top 10% Undergraduate GPA
GRE: Verbal 160
IELTS: 7.5
CET-6