How we score ourselves

Why this stack

Thomson Reuters News Analytics and PsychSignal were paid firehoses. The 2026 open-source ranking for finance is clear:

• FinBERT (finbert.org) — live. 86–97% on Financial PhraseBank. Domain-trained on SEC filings and news. Headlines scored through the Pro cloud API, then blended with FinLex.
• World Monitor equity layer — live. Server-authoritative Country Instability Index across 31 strategic states, Hormuz/Kerch chokepoints, Polymarket probabilities, and four engineered feature classes (level, delta, divergence, convergence). Mapped onto listed names with named drivers. The desk takes that as a 10% sleeve so Massive + FinBERT still dominate.
• FinGPT v3 — LoRA-tuned LLM, strongest on several finance sets, needs a GPU. Reserved for a later training cluster, not the live desk.
• FinLex — Loughran–McDonald + VADER valence + earnings phrases. Always on, transparent, and the fallback when FinBERT is cold.
• TMX Global events — live calendar via Massive (earnings, dividends, splits, conferences). Shown on the ticket. If a print sits inside the five-day window we flag it. It does not rewrite the published score.
• Options shadow (options_v1) — live, not the book. CBOE delayed chain (Massive if the key is entitled): ATM IV, 5-day implied move, put/call skew, volume ratio, term. Scored with the same 1% dead-band and stored beside the ticket so we can promote it only if residual IC beats the hybrid. It never writes methodology_v1.

5-day path

The original Watstock research used a CNN + LSTM on ~100 technical and TRNA features. The production hybrid here keeps that shape without a GPU:

• CNN-like — 5-vs-5 return/volume sequence window
• LSTM-like — 5-day return persistence + MACD memory
• XGBoost-like — direction tree on trend, momentum, RSI, sentiment
• Technicals — SMA/EMA, MACD, RSI, ATR, Bollinger, Stochastic, Aroon, OBV
• Sentiment — FinBERT.org neural score blended with FinLex
• Geo — World Monitor equity layer: CII, chokepoints, prediction markets, divergence/convergence
• Tape — Massive licensed aggregates, last print, and news

Weights: ~30% technical score, ~25% news, ~14% sequence, ~10% persistence, ~11% direction tree, ~10% World Monitor geo, then ATR-scaled so a utility and a semiconductor do not share the same implied move. Elevated US CII is a risk-off tilt. Hormuz / strait stress supports tankers and crude proxies and is a drag on carriers. China–Taiwan stress is a drag on the semi stack. Active European conflict and GPS/jamming language support defense industrials and gold. Divergence (a signal without a priced move) is the alpha-bearing class; convergence fires the escalation strip.

Crypto book (crypto_v1)

A separate desk at /crypto under the same Pro plan. It does not write methodology_v1. Horizon is five calendar days (24/7). BUY if 5-day USD ≥ +3%. SELL if ≤ −3%. HOLD inside that band. Dollar pegs (USDT, USDC, DAI) are HOLD while the peg holds; a print below 0.98 is SELL. Top-10 holders above 75% block a BUY. Onchain firehose is Etherscan Pro Plus; price path may also print from Massive. WATSTOCK does not hold keys or route swaps.

Five Sessions (studio)

A human rundown of the published top ten. Live for Pro, Mondays 09:00 GST from DIFC. Public after the five sessions, with a forensic post-mortem. The show reads the book. It does not write methodology_v1. Every Pro seat is watermarked; a leak traces to the seat.

Signal-to-instrument map

Every World Monitor family is wired to the listed names it most plausibly leads. The event-alpha sheet on World Monitor is this map, live.

• CII levels and 24-hour deltas → country ETFs (EWZ, EWW, TUR, KSA, UAE)
• Prediction-market shifts → defense primes, energy majors, VXX
• Hormuz / chokepoints → FRO, STNG, USO, BNO, refiners; airlines inverse
• GPS / jamming / OREF → LMT, RTX, NOC, GLD
• Cyber IOC language → CRWD, PANW, FTNT
• Critical minerals → ALB, MP
• Climate / crop stress → DBA

A forecast that names its drivers is auditable. The product is information and media — you keep discretion. This is not advice.

Buy, hold, sell

• BUY — expected 5-day return above +1.65% and sentiment not clearly negative.
• SELL — expected 5-day return below −1.65% and sentiment not clearly positive.
• HOLD — everything else, including RSI extremes that fight the tape.

Scoreboard

Every published call is written before the fact and resolved against market prices after the fact. The correctness rule is fixed, published, and never tuned after the fact. It is methodology_v1:

• BUY is correct when return is at least +1.0%
• SELL is correct when return is at most −1.0%
• HOLD is correct when the absolute return is under 1.0%

The 1.0% dead band exists so HOLD is a real call, not a free win. A name with fewer than 10 resolved predictions shows “insufficient history”, never a percentage. If the rule must evolve it becomes methodology_v2 and scores forward only. We never rescore the past.

What we claim, and refuse to claim

WATSTOCK claims exactly one thing: that its record is real. We refuse to claim accuracy percentages as marketing, guaranteed returns, or predictive certainty of any kind.

Free media

The ranking, five-session scores, Studio, and the public scoreboard are free. There is no paid book. Sign in only if you want a watchlist or the paper simulator. Charging for the week ahead would look like advice. We would rather be a show.

Paper book

Open an account. Each book starts with $100,000 virtual cash. A mock fill uses the last session close. This is a simulator for learning — not a ticket you send to a bank, and not advice.