Agentic Screening · Self-Optimizing

Stock Screener Optimized.
The screen that tunes itself.

An autonomous equity screener that gates on a backtested macro model before it spends a dollar of attention, hunts multi-year outperformers printing fresh all-time highs, verifies its own work, and feeds every run back into its next version. It runs unattended three times a market day — and it gets sharper the longer it runs.

Macro Sharpe
0.71
vs 0.57 buy & hold
Directional Accuracy
56.7%
p < 0.0001, 7yr walk-forward
Backtest CAGR
11.8%
vs 9.8% buy & hold
Cadence
3×/day
unattended, Mon–Fri

How it works

A funnel with a brain on the front of it

Most screeners are a dumb filter: point them at the market, get a list. This one starts by asking a different question — should I even be buying today? A logistic-regression macro model reads the yield-curve slope, the change in Fed Funds, the VIX, and short-term momentum, and emits a single bullish/bearish probability. On risk-off tape it sits out by design and posts an alert. Only when the regime is favorable does the screen run.

When it runs, it pulls every stock printing a new 52-week high across the NYSE, NASDAQ, and CBOE, then squeezes them through two quantitative passes: +100% or more over the last year, then +500% or more over ten years, still within a whisker of its all-time high, still trending. Survivors are the >5x/10y list — companies that have compounded for a decade and are still making new highs.

Then the agent does the part most tools skip: it checks its own work. It re-verifies a random sample of the stocks it rejected, flags any candidate whose gains came from a single suspicious quarter or a sub-$2 penny-stock origin, and compares today's hits against the last run to catch silent regressions. Results go to Telegram and to this page; new names are synced into the live buy-and-hold portfolio sheet. No human in the loop.

01

Macro gate

LogReg model on yield curve, Fed Funds, VIX & momentum decides bullish vs. bearish. Bearish → alert and stop.

02

Scan 52-wk highs

Pull every new 52-week high on NYSE / NASDAQ / CBOE (IPO > 1yr) from Finviz.

03

Pass 1 · 1-year

Download 2yr quarterly OHLC, keep only names up ≥ 100% over the last year.

04

Pass 2 · 10-year

Download 10yr history; require ≥ 500%, a fresh all-time high, and positive momentum.

05

Guard & verify

Forbidden-proxy guards, random spot-check re-verification of rejects, regression check vs. the prior run.

06

Broadcast & sync

Post results to Telegram and this page; append new names to the buy-and-hold portfolio sheet.


Why it gets better

The Karpathy optimization loop, running in production.

Most “AI tools” are frozen the day they ship. This one isn’t — it is built around a loop that treats its own track record as training data.

Andrej Karpathy’s framing of modern AI — Software 2.0, and the Tesla “Data Engine” flywheel — is that you don’t hand-write the rules. You specify a goal, then let an optimization loop improve the system by closing the gap between what it predicted and what actually happened. It is the same loop that trains a neural network — predict, measure the error, adjust, repeat — except run continuously, in production, where every real-world outcome becomes the next lesson. This screener is that loop wearing a finance hat:

Predict

Run

The macro model scores the regime; the funnel emits candidate hits. 3× every market day.

Observe

Log

Every run appends a labeled record to run_log.jsonl — signal, macro inputs, funnel counts, hits.

Measure loss

Evaluate

Backtest accuracy & Sharpe; live regression alerts and spot-checks are the production error signal.

Update

Retune

Model coefficients and every threshold live in config, re-fit from the accumulated log — not hand-coded.

Redeploy

Repeat

The tuned model ships and runs again. Each cycle adds another labeled example to the flywheel.

↻  closes every run · the data engine compounds

The payoff is concrete. The 50-day moving-average filter the screener started with was a static rule someone guessed. It was replaced by a logistic-regression model fit on seven years of data — lifting backtested Sharpe from 0.57 to 0.71 and turning a hand-picked threshold into eight learned coefficients that any future run can re-fit. That is the difference between a script and an agent: a script does the same thing forever; an agent uses its own production logs to write its next version.


Live performance

Latest screen.

Auto-published by the agent on every run — the same output that goes to the Telegram channel. The macro signal, the funnel, and the candidate stats are public; the live symbols are a subscriber signal.

LIVE Latest screen · 2026-06-08 12:03 CST · 230s
MACRO: BULLISH — screen ran
Score+0.1400
VIX18.3
Yield curve Δ+0.159
Fed Funds Δ+0.033
SPY mom 5d-2.3%
SPY RSI51.7
Finviz 178 Pass 1 18 Pass 2 0 Hits 0
>5x/10y candidates (10yr ≥ 500%, 1yr ≥ 100%): 0

No names cleared the funnel this run.

Live symbols are a subscriber signal.
The macro read, the funnel, and the candidate stats are public — the tickers ship to M.A.X. Signals subscribers (from $29/mo).
Get the live signals →

Under the hood

The macro model.

A logistic-regression classifier trained in our GPD research framework on 2018–2025 market data with walk-forward cross-validation. It replaced a single hand-set moving-average rule — the first turn of the optimization loop above.

ModelLogistic Regression (sklearn)
Backtest window2018–2025 · 7yr walk-forward CV
Directional accuracy56.7%  (p < 0.0001)
Sharpe ratio0.71  vs  0.57 B&H
CAGR11.8%  vs  9.8% B&H
Max drawdown−33.5%  vs  −35.7% B&H
Decision rulescore > 0 → run screen
FallbackSPY > 50-day MA if data unavailable
Yield-curve slope Δ + Fed Funds 3m Δ VIX level SPY 5d momentum TLT momentum + SPY z-score +
Disclosure

This page documents an autonomous research and screening system operated by CSI Automation. Screen output is a quantitative signal, not investment advice and not a solicitation. Backtested results are hypothetical, reflect a specific model over a specific window, and do not predict future returns. Live candidate symbols are withheld; nothing here is a recommendation to buy or sell any security.


← Back to all projects