Recession risk, scored the way it would have been scored at the time.
A single monthly score built from eight economic indicators, computed each month using only the data that had actually been published by then. Then held to that record, without hindsight.
Illustrative, from the validation record. The live reading is available to beta subscribers.
What you get each month
One number, one regime, and the reasons behind it. Published once, on a fixed schedule, and never revised after the fact.
Recession Risk Score, 0–100
Where this month's model output sits against its own history. Above 60 is Elevated; above 85 is High. Thresholds were fixed before validation, not tuned to fit it.
Why it moved
An explanation panel shows which of the eight inputs pushed the score up or down: the yield curve, labour market, industrial production, housing starts, consumer sentiment and equity returns.
Market Stress Monitor
A separate, descriptive 0–100 reading of drawdown and volatility conditions. It says how stressed markets are now; it does not claim to predict them.
Validated on data as first published
Most recession models are tested on today's revised data, which nobody had at the time. VALTIVRA is tested on the numbers that were actually available each month, using the Federal Reserve's ALFRED archive of historical data releases.
0.82Point-in-time AUROC (95% CI 0.67–0.94)
332out-of-sample months
3recessions in the test period
0revisions to any published score
Each month's score is generated by a model refit only on information available up to twelve months earlier, so the test is a fair one: it could have been run live. The methodology is frozen and documented, and any change to the inputs, the model or the thresholds requires a designated new version and a full re-run of the validation.
The record includes the failures, because a track record without them is not a track record.
False alarms: the score entered the Elevated regime in 2005–06 and again in 2022–24 without an NBER recession following.
Ranking skill is weaker in the most recent decade (2017–26) than over the full sample.
2020 is described only as "entered the Elevated-risk regime"; no model anticipated a pandemic.
The score is a ranking, not a probability. A calibrated probability is shown separately and is labelled as not validated.
Who it is for
Professionals who already form a view on the cycle and want one disciplined, auditable input alongside their own judgement.
Investment advisers and family officesA consistent talking point for client reviews and a documented basis for defensive positioning.
Corporate treasury and financeA monthly regime signal for liquidity, hiring and capital-spending planning cycles.
Banks and credit unionsA point-in-time macro overlay for credit committees and allowance discussions.
Economists and research teamsA transparent baseline with its full validation record and specification available to read.
Private beta
We are onboarding a small group of professional users, fewer than fifty seats, while data licensing and an independent validation review are completed.
Monthly score, regime, trend and explanation panel
Market Stress Monitor
Full methodology specification and validation record
Direct line to the developer; your feedback shapes the paid product
Tell us who you are and how you would use it. Invitations go out in batches.