USD
EUR
HKD
Financial Intelligence Platform · 2026-06-05 14:42 UTC

Financial intelligence,
made legible.

SAINHE is an independent financial intelligence platform. It aggregates macro signals, decodes SEC filings, prices assets, and explains market structure — so you think for yourself and act with conviction.

Dashboard Stock Analysis Learn Get in Touch
Get in Touch · Built by one person, for anyone who wants a clearer view of the markets.

Who's behind SAINHE

H
Hugo Waldmeyer
Founder & Creator · SAINHE
Finance student, last year of my bachelor's. I designed, built, and maintain this entire project — from the data pipeline to the dashboard. No team, no budget. Just the right questions asked to the right tools.
@hugo_wdmr View source on GitHub
The code is open
The full codebase is on GitHub — data pipeline, signal logic, dashboard rendering, everything. If you're curious about how any of it works, or want to understand a specific metric, it's all there to read. github.com/mugiwara95d/sainhe-v3 →

Why this project exists

This started as a personal tool. I wanted to make better financial decisions for myself — not trade professionally, just understand what's actually happening in the markets at any given moment.

The problem is that the tools that actually work at a serious level are out of reach for most people. High-frequency infrastructure, quantitative systems, exclusive data feeds — these aren't available to someone sitting in a finance class. And trading algorithms lose to transaction fees before they even start. My classes taught me theory, but they never told me what to actually look for when making a decision.

So I built a different kind of edge. Not faster trades — better context. SAINHE pulls together the signals that institutional analysts watch: ERP, yield curve, VIX regime, HY spreads, sector rotation. Aggregated automatically, explained clearly, no paywall.

I built all of this without writing a single line of code myself. That's not a disclaimer — it's the point. Knowing what to ask, what to look for, and how to think critically about a problem is a skill. The tool is AI. The judgment is human. In a job market where tens of thousands of people apply for a single finance role, I'd rather show what I can actually do.

Feedback

All of it welcome

Whether something works exactly as you'd expect, something looks off, or something important is missing entirely — I want to hear it. Positive feedback tells me what's worth keeping. Negative feedback helps me fix things I can't see from the inside. Either way, reach out directly on Instagram.

If a number looks wrong — a value that seems stale, a metric that doesn't match what you see elsewhere — send me the ticker or metric name and what you'd expect to see. That kind of feedback is especially useful.

Drop a message
The easiest way to reach me is on Instagram: @hugo_wdmr. I read everything.

What's next

In progress
Stock Analysis — AI Agent
In progress
Top-down analysis is the standard institutional framework for a reason: validating the macro environment and sector momentum before touching a single stock eliminates the majority of losing trades before they start. Reading SEC filings directly — 10-K, 10-Q — closes the information gap between retail and professional research desks, because filings carry legal liability in a way that earnings calls and press releases don't.
Full pipeline
Macro check
Is the macro environment favorable? VIX regime, ERP, yield curve, global liquidity.
→
Sector health
Is the sector in a growth or rotation phase? Relative strength, valuation vs peers.
→
Volume validation
Is there institutional buying confirmation? OBV trend, RVOL, MFI signal.
→
SEC analysis
What does the actual filing say? Revenue quality, debt structure, guidance vs reality.
Portfolio Simulation
Planned
Position sizing and correlation between holdings drive risk-adjusted returns far more than stock selection alone — a concentrated portfolio of uncorrelated positions consistently outperforms a diversified list of average picks. Beta measures how much each asset amplifies or dampens overall portfolio moves: two high-beta positions in the same sector don't diversify risk, they stack it — knowing the correlation matrix before sizing is the difference between intended and accidental exposure. Simulating a portfolio against historical macro regimes (rate shock, VIX spike, sector rotation) lets you stress-test your allocation before the market charges you for the lesson.
Quantitative Factor Models
Exploring
Factor models — value, momentum, quality, size — explain the majority of cross-sectional return variance across markets, and systematic exposure to factors is how most institutional alpha is actually generated, not individual stock picking. Backtesting these signals against historical data is the only way to distinguish real edge from hindsight bias, which is why every serious quant desk starts there.
SAINHE pipeline Fetch→ Compute→ Render→ Read