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.

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.

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 decision-support analytics — you keep discretion, and we stay on the research side of the advisory line.

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. Prior materials asserting figures of that sort — including the withdrawn 2017 plan — form no part of the product.

Free and Pro

Daily sentiment and the public scoreboard are free. Five-session calls, the top 10 of the ranking, unlimited watchlists, and alerts are Pro at $7.99 per week or $24.99 per month, billed through Stripe. The free tier is the trial, permanently. The scoreboard is the salesperson.

Paper book and bank tickets

Open an account. Each book starts with $100,000 virtual cash. A mock fill uses the last session close. “Send to bank” issues a signed instruction you share — copy, download, email, SMS, or the phone share sheet — into your banking or brokerage app. We also deep-link to Fidelity, Schwab, IBKR, Robinhood, and E*TRADE research pages. We never transmit an order.

Services you can subscribe to

Nothing is required to run the desk. These keys upgrade the same app without a rewrite:

• Massive — live. Formerly Polygon.io. Licensed US daily bars, snapshot last print, reference names, and news. Set MASSIVE_API_KEY.
• World Monitor — live. Pro enterprise API. Equity layer: CII, country briefs, chokepoints, prediction markets, and market-transmission cards. Set WORLD_MONITOR_API_KEY.
• Twelve Data — alternative tape. Set TWELVEDATA_API_KEY.
• Hugging Face — live. Official ProsusAI/finbert weights. Set HF_TOKEN.
• finbert.org — live backup. Pro cloud API, same three-class model. Set FINBERT_API_KEY.
• Neon / Postgres — durable accounts and paper books. Set DATABASE_URL. Docker Compose includes Postgres.