Research-backed answers to the biggest questions about AI trading, alternative data, and autonomous agents.
What the research says about AI trading performance, and what Fin45 is testing in real time.
The truth about AI trading bot performance — survivorship bias, backtesting traps, and live results.
How autonomous AI agents differ from algorithmic trading, quant funds, and simple bots.
SEC Form 4 filings, cluster buys, and signal scoring — a guide to legal insider trade analysis.
The STOCK Act, disclosure timelines, and how to use congressional trading data in your research.
Off-exchange volume, FINRA ADF prints, and why dark pool activity signals institutional intent.
Comparing AI agent strengths (speed, consistency, data throughput) against human edge (intuition, narrative).
From satellite imagery to patent filings — how non-traditional data creates information edges.
NLP on transcripts, sentiment scoring, and detecting management confidence signals.
Position sizing math for uncertain outcomes — why Fin45 uses Half-Kelly instead of full Kelly.
Sweep orders, unusual volume, and premium signals that reveal institutional conviction.
Why requiring multiple independent confirmations dramatically reduces false positives.
Using Polymarket, Kalshi, and Metaculus probabilities as trading signals.
The honest comparison — expected returns, risk profiles, costs, and what the evidence says.
Capital requirements from paper trading ($0) to live deployment. PDT rules and position sizing.
34 key terms defined — from alpha decay to trailing stops. The language of autonomous trading.
Financial forensics: Beneish M-Score, cash flow divergence, accrual quality, and AI deception scoring on live calls.
Understanding SEC 13F filings — what they reveal about hedge fund positions and why delayed data still matters.
The mechanics of forced covering, how to spot squeeze setups, and what the data shows about squeeze outcomes.
Which filings matter most — Form 4, 13F, 8-K, 10-K — and how AI extracts signals from regulatory data.
How NLP extracts trading signals from earnings calls, news, and social media. Which sentiment sources predict returns.
Congressional trading disclosure law — what it requires, where enforcement fails, and how to use the data.