Sydney · data & automation · software

Hi, I'm Haokai Tan Data Analyst / Automation Developer

View Projects Get In Touch

Master of Data Science and Decisions graduate from UNSW, now building production data and automation systems full-time for a distributed overseas team.

I turn operational problems into reliable workflows, analytics APIs, and decision-ready tools using Python, SQL, FastAPI, Next.js, and Docker.

Working Stack

Python SQL FastAPI Docker Data Quality

Tech Stack

React
JavaScript
TypeScript
Tailwind CSS
HTML5
CSS3
Node.js
Python
SQL
MongoDB
R/RStudio
PostgreSQL
Git
Figma

What I do?

I translate operational questions into reliable data products, automated workflows, and decision-ready reporting.

My Projects

Selected builds shown as working systems, research artifacts, and anonymized production patterns.

Discord automation 2024

Discord TTS Bot

Makes Discord voice activity visible through scheduled reports, co-presence analysis, and real-time TTS notifications.

Voice joins / leaves Rankings + heatmaps MongoDB + JSON fallback
Python Discord.py MongoDB Docker TTS
View Code
Voice puzzle game 2024

One in Four

Lateral Thinking Puzzle Game with Voice Interaction. An interactive terminal-based game combining AI, voice input, and text-to-speech technologies.

jQuery Terminal UI WAV voice input AI spoken response
Express.js jQuery Terminal OpenAI ElevenLabs WAV Audio
View Code
Real ops automation 2024

WFX Dropbox

Automated WorkflowMax to Dropbox folder synchronization tool. Polls WorkflowMax API, creates job-specific Dropbox folders with custom naming conventions.

Scheduled polling Template folder copy Duplicate prevention
Node.js Express.js Dropbox API OAuth 2.0 Automation
View Code
Research publication Second author

Classical Feature Embeddings Help in BERT-Based Human Mobility Prediction

Second-author research paper on STaBERT, a semantic-temporal BERT mobility model that fuses POI embeddings and temporal descriptors for stronger trajectory prediction.

RoleSecond author
VenueSIGSPATIAL 2025
Reported lift0.34 to 0.75 GEO-BLEU
STaBERT BERT Human Mobility POI Temporal Features
Read arXiv Open DOI
Project index Public + anonymized

Additional Work

Smaller public repos and private system patterns, listed only when they show a distinct build capability.

Public GitHub Repos

GL_Fusion GNN + LLM mobility forecasting research optimized for HPC-style training workflows. Jupyter · GNN · LLM · DeepSpeed · HPC WFX-Timesheet Timesheet reconciliation workflow for operations data and discrepancy review. JavaScript · Workflow · Automation VCN Early platform prototype for service orchestration and data workflows. Python · Platform · Prototype

Anonymized Docker Patterns

Ops Scheduling Platform

Offline-first scheduling dashboard with recurring templates, analytics, and spreadsheet sync.

Next.js · FastAPI · SQLite · Sheets Sync · Docker
Training Simulation Workspace

Role-based live chat simulation with trainer review, session history, and AI draft scoring.

React · API · SQLite · AI Review · Docker
Message Intelligence Bot

Scheduled channel summaries with hierarchical rollups, trend context, and management-ready digests.

Python · LLM · Scheduler · Summaries · Docker
Operations & Analytics Platform

Production platform connecting 27 registered data sources with analytics APIs, scheduled workflows, and 12 cross-domain quality checks.

Python · SQL · FastAPI · Next.js · TypeScript · Docker
View All Projects

Instagram

Personal snapshots, Sydney moments, and everyday life.

Let's Connect

Have a project in mind or just want to chat?

Get in Touch

Whether you have a specific project, a question about my work, or just want to connect, I'd love to hear from you.

Location

Sydney, Australia

Email

tan@haokaiii.com

Connect on Social

Send a Message