Prediction markets & the AI macro brief
Finisdom’s Macro Overview turns real-money prediction-market prices into plain probabilities for the events that move every portfolio, then pairs them with a weekly AI-written brief that synthesizes the regime, valuation, and positioning into one honest read — conditions and base rates, never a forecast.
What it does
- Real-money implied odds for the next Fed decision, rate cuts, recession, inflation, and GDP
- Sourced from Kalshi — reported as what the market prices, never as a Finisdom forecast
- A weekly brief Claude writes from Finisdom’s own deterministic readings
- Synthesizes the deployment gate, regime, valuation, and futures positioning into one read
- States conditions and historical base rates — never a price prediction
- Delivered on the Macro Overview page and, for members who opt in, by email
How it works
Read the odds
Market-implied probabilities for curated macro events, updated as Kalshi prices move.
Get the weekly synthesis
Every week, Claude reads the gate, regime, valuation, and positioning data and writes a plain-English brief.
Judge the conditions, not a call
Both surfaces report what the evidence says right now — never a prediction of what happens next.
Frequently asked
What is a prediction market?
A prediction market lets people trade contracts that pay out based on whether a real-world event happens — a Fed rate decision, an inflation reading, a recession call. The price of the contract is, in effect, the market’s real-money implied probability of that outcome.
Are Kalshi’s odds a forecast from Finisdom?
No. Finisdom displays what the market is pricing — real traders risking real money — as context, not as our own prediction. The odds can be wrong, and thin or newly listed markets carry extra liquidity risk.
What exactly is the Weekly AI Macro Brief?
A short, Claude-written synthesis of Finisdom’s own deterministic signals — the six-signal deployment gate, market regime, Shiller CAPE valuation, CFTC futures positioning, and the prediction-market odds — read out in plain English once a week. It is built to describe conditions and historical base rates, not to call the market’s next move.
Is the brief investment advice?
No. It is educational analysis of current conditions, generated from the same deterministic evidence shown elsewhere in the cockpit, and it always says so. It never recommends a trade and never predicts a price.
Is this free?
The Macro Overview page — including the event odds and the weekly brief — is part of the Finisdom cockpit, available to members. The concepts behind prediction markets and market regimes are explained for free in the Learn section.
More Finisdom tools
Backtest any multi-asset portfolio against decades of real history — Sharpe, Sortino, Calmar, max drawdown, rolling returns, and crash stress tests, benchmarked and split by bull and bear regimes.
Trace the efficient frontier for any set of assets and compare max-Sharpe, min-volatility, equal-weight, inverse-vol, and risk-parity allocations — with honest walk-forward validation, not a curve fit.
Decompose any portfolio’s return against its benchmark — allocation, selection, and interaction effects — with factor-risk exposures, tracking error, information ratio, and marginal contribution to risk (MCTR).
A single 0–100 read on whether the market backdrop favours deploying capital or holding back — built from trend, credit, volatility, and breadth signals, with an S&P 500 deployment-zone overlay.
Pair a disciplined quant signal with a Claude fundamental-quality review, blended into one verdict — momentum, value, and quality scored by the engine, business durability read by the model.
Test a whole library of rule-based timing strategies on any instrument through a robustness funnel — an out-of-sample split, six pass/fail filters, and a permutation “skill vs luck” test — to see how few actually survive.
Track a dozen economically-linked pairs — gold vs real yields, credit vs stocks, the 60/40 hedge — and see which have pulled apart from their own norm, each with the historical base rates of what followed.
What actually happened after past earnings surprises: every reported quarter since 2008 pooled and bucketed by surprise size, with the forward drift at 5, 21, and 63 sessions and the sample size on every number.
Ten concentrated, actively-managed funds — their largest positions, what they opened, exited, added and trimmed last quarter, and where any of it overlaps your own book. Index giants deliberately excluded.
Design a fund as a rule rather than a basket, replay it point-in-time across decades, then freeze it and publish it to a leaderboard that ranks funds on how much of their backtest they actually kept.
Backtests and optimizations are hypothetical illustrations built from historical data — not predictions, and not investment advice. Past performance does not guarantee future results.