Are you going to keep checking 2,500 stocks by hand every day?
After the market closes, you search Naver Finance for stocks that have surged,
read the news to decide whether it’s good or bad,
check foreign and institutional investor flows one by one,
open charts and analyze their patterns...
Do you find yourself doing this every day?
I did, too.
I spent 2–3 hours after work analyzing stocks, and still missed more stocks than I could keep up with.
There are over 2,500 stocks on the KOSPI and KOSDAQ combined. One person simply can’t review them all every day.
---
So I built a system
I built a system that automatically analyzes 2,500 stocks every day after the market closes.
- It automatically collects prices, investor flows, and news
- AI (Gemini) reads the news and determines whether it’s positive or negative
- It scores each stock out of 15 using six factors
- It selects only stocks that meet the criteria and calculates entry, stop-loss, and take-profit prices
- It sends alerts through Telegram
All I have to do is check my phone after work.
Then, every Saturday, the system analyzes the previous week’s performance and automatically adjusts its stop-loss levels, take-profit levels, and holding period.
It’s designed to learn and improve on its own.
---
But I’m not a developer
I didn’t write the code for this system myself.
I built the whole thing by telling AI what to do.
"Filter out stocks that rose more than 5% today and had over 50 billion won in trading value."
"Send these three news articles to Gemini and have it determine whether they’re positive or negative."
"Create a scheduler that runs automatically at 4 p.m. every day."
When I say things like this, AI (Claude) writes the code for me.
This is vibe coding.
---
You’ll build this exact same system in this course
Across 58 lessons, we’ll build from scratch the system I actually use every day.
Starting with data collection,
we’ll cover AI news analysis, a scoring engine, signal generation,
a Flask API server, a Next.js web dashboard,
automated Telegram alerts, and even a self-learning system.
A Jupyter notebook isn’t the end product.
The end product is a web dashboard that runs every day and sends Telegram alerts.
You don’t need to know how to code.
In each lesson, I’ll show you exactly what to tell Claude,
and if you follow along, you’ll get the same results.
---
Recommended for
- Working investors who don’t have enough time to analyze stocks every day
- Anyone who wants an automated system but doesn’t know how to code
- Anyone curious about quant or systematic trading but unsure where to start
- Anyone who wants to learn how to use AI in practice
---
⚠️ This course does not guarantee investment returns.
It’s a programming course where you’ll build your own stock analysis tool.
Each student is responsible for their own actual investment decisions.