🌐

Data Science + Economics

Hello world, my name is Howard.

or 胡昊阳

Trying to build the future before it becomes obvious.

SQL Python Power BI Tableau A/B Testing Hypothesis Testing TensorFlow PyTorch Google Cloud AWS OpenClaw Azure SQL Python Power BI Tableau A/B Testing Hypothesis Testing TensorFlow PyTorch Google Cloud AWS OpenClaw Azure

Projects

This is the part I care most about: building systems that can run on their own, keep me informed, and turn information into useful outputs.

Flagship System

JARVIS

A personal AI operating system

Stark Industries was fictional. The idea wasn’t.

JARVIS began as a simple question: what if I had a real digital teammate I could talk to all day, not just another chat window?

Instead of typing prompts, I wanted to say things like: “Jarvis, what’s on my agenda today?” or “Research this topic and build a full execution plan.”

JARVIS is my attempt to build that system.

It combines voice interaction with a modular agent architecture capable of research, synthesis, monitoring, and action. Under the hood, specialized agents coordinate tasks like web research, information extraction, summarization, and automated execution.

Rather than a single chatbot, JARVIS functions as a personal AI operating layer, a system that can run workflows end-to-end, from gathering information to producing usable outputs.

The long-term vision is a persistent AI partner that understands context, manages complex tasks, and acts as an always-available digital teammate.

This prototype explores that architecture through OpenClaw-style autonomous browsing, LLM orchestration, and real-time voice interaction.

PYTHON · LLM APIs · AGENT ORCHESTRATION · WEB AUTOMATION · VOICE INTERFACES · OPENCLAW-STYLE SYSTEMS

Automation

Brainrot Content Factory

An automated pipeline for short-form media

Dopamine maxing by putting shorts content creation on autopilot.

This started as an experiment in scale: how far can I push a media pipeline before manual bottlenecks show up? The system detects trend signals, builds scripts, generates visuals, and assembles shorts with minimal intervention.

I also built in quality gates around timing, hook strength, and visual continuity so it’s not just auto-generated noise. The end goal is a repeatable engine for autonomous content channels.

Python · Sora · FFmpeg · Platform APIs

Data Visualization

Analytic Dashboard Maker

From raw tables to decision-ready dashboards

Because manually rebuilding dashboards every week is character development I did not need.

This project came from seeing how much analyst time gets burned cleaning data and redoing the same visuals. I built a pipeline that ingests messy business data, extracts key metrics, and prepares dashboard-ready structures with much less manual work.

I focused on making outputs practical: clear KPI definitions, reusable transformations, and automated handoff into BI tools so teams can spend more time deciding and less time wrangling.

Python · Power BI · SQL · Workflow automation

Research Infrastructure

Curiosity X

Continuous monitoring of the internet

My personal intel feed, minus the 20-tab chaos.

I built this because I was spending too much time context switching between feeds, forums, and tech news. The agent continuously monitors sources and compiles concise briefings.

It prioritizes what matters, summarizes developments with clear action points, and pushes updates through messaging so I can react fast without manual hunting.

Python · RSS ingestion · LLM summarization

Visual Storytelling

Photography Studio

People, light, and memory-driven frames

A separate visual module for film, graduation, gigs, and experimental work.

This project page is where I curate my photography work as a clean gallery experience. It includes categorized collections, fullscreen browsing, and fast navigation so the images stay the main focus.

Film · Graduation · Gig Works · Shenanigans

Open project

About

I am a UC Berkeley student pursuing dual B.A. degrees in Data Science and Economics. I focus on analytics, business intelligence, and experimentation to turn complex datasets into clear decisions.

My work spans SQL data pipelines, Power BI/Tableau dashboards, forecasting, NLP sentiment analysis, and machine learning model collaboration. I am currently open to internships and full-time opportunities in data and BI.

Lately I’ve been especially into experiment design, dashboard automation, and turning rough ideas into systems people actually use. I optimize for clarity, speed, and outputs that are practical in real team workflows.

Education

University of California, Berkeley

Aug 2022 - May 2026 · Data Science and Economics

Work Experience

Click a role to open details.

I’ll be helping enterprise teams translate AI strategy into working architectures they can actually deploy and scale.

What excites me most is the blend of technical depth and people work: building MVPs, guiding adoption, and being the bridge between business goals and implementation reality.

Python · LLMs · Watsonx · Solution architecture

I rebuilt messy finance data workflows into clean SQL pipelines and cut processing friction by 200%, so reporting became much faster and more reliable.

I learned how much good analytics depends on trust and maintainability, not just smart queries, and focused on building dashboards and automation the team could keep using.

SQL · Power BI · DAX · Power Automate

I worked on behavior and review data to help connect customer signals to better product and marketing decisions.

I left this role with stronger instincts for turning raw data into decisions people can actually act on, not just charts that look good in a deck.

BigQuery · Python · NLP · TensorFlow · PyTorch

I blended campaign data with merchandising signals to shape promotions that actually moved traffic and conversion.

We drove a 25% CTR increase and 150% sales lift, and I learned how fast iteration plus clear metrics can outperform perfect plans.

BI · Marketing analytics · Growth strategy