Pancis 1.0 AI model
COLDSTREET / MACROECONOMIC INTELLIGENCE

Pancis 1.0
AI model

Understand the outlook. Inspect the evidence.

Pancis 1.0 brings Coldstreet’s macroeconomic forecasting research, data library and methodology into one place. It is a suite of statistical and machine-learning research workflows, with separate models for policy rates, inflation and employment.

Country registry195

Coverage is broader than forecast availability

Rate forecast horizon2 months

August origin → October 2026 month-end

Model statusResearch

No model promoted to production

INSIDE PANCIS / ARCHITECTURE

Mixture of experts

Three specialist models. One evidence-based routing decision.

RESEARCH CANDIDATE
01 · EVIDENCEAuthority history + cycle signals
02 · CHOOSE AN EXPERT TO EXPLORE
03 · EVIDENCE-BASED ROUTEROne expert selectedAuthority + cycle → broader evidence → baseline fallback
04 · SELECTED EXPERT’S SCORES
CutHoldHike
How routing uses historical evidence

Annual selection uses only outcomes before the forecast year. Minimum support is checked for authority + cycle, authority, cycle and global evidence. Small samples are adjusted toward global performance. The selected expert supplies all three scores.

01 / EVIDENCE

Authority & cycle

Policy history
Calendar & macro signals
Current cycle segment

02 / EXPERT POOL
03 / ROUTER

Select an expert

Best supported, adjusted balanced accuracy

Authority + cycleAuthorityCycle segmentGlobal evidence
Insufficient support → baseline champion
04 / OUTPUT

Selected scores

CutHoldHike

Use the selected expert’s three direction scores.

Next-calendar-month research target
EXPLORE AN EXPERT

Baseline champion

The frozen recent-own-calendar / PPI-missingness expert supplies the baseline direction scores. It is also the fallback when the router lacks sufficient historical support.

Click an expert above to inspect its role. This highlights the architecture; it does not change a live forecast.
History before the forecast year

Annual routing uses matched out-of-fold predictions with target dates strictly before January 1 of the forecast year.

Small samples get less influence

Local class recall is adjusted toward global evidence. Each routing level must pass minimum sample and cut/hold/hike support requirements.

One expert supplies the output

This experiment uses hard routing: it selects a single expert for an authority and cycle segment rather than averaging all three score vectors.

Architecture evidence & evaluation

The configured expert priority is champion → compact → full. Minimum support is 72 rows and 4 cases per class for authority + cycle; 96 / 5 for authority; and 180 / 10 for cycle or global routing. Local estimates use a global prior equivalent to 25 rows per class.

On the reused 7,583-case, 39-authority development set, this MoE candidate reached 68.36% balanced accuracy, compared with 68.76% for the frozen champion. Recent-period scores were 59.06% and 58.69%, respectively. These next-month results do not validate the current two-month outlook.

Download architecture & source references ↗

Documented support-shrunk mixture-of-experts experiment. It has not been promoted and does not replace the current country forecast selector.

FROM EVIDENCE TO OUTLOOK

How Pancis works

Full methodology ↗
  1. 01

    Gather the evidence

    Policy-rate histories, inflation, producer prices and unemployment form the forecasting evidence. Source records retain their dates, units and available provenance. Country fundamentals and the event calendar add context; their presence in the library does not mean every field is a model input.

  2. 02

    Align countries and time

    Countries are mapped to their monetary authority and policy instrument. Members of a currency union share an authority rather than becoming independent rate observations. Histories are aligned to a forecast origin; missing or stale inputs can block issuance.

  3. 03

    Generate candidate forecasts

    Separate models answer separate questions: the direction of a rate move, the distribution of possible move sizes, and future macroeconomic values. Local forecasts, cross-country candidates and persistence baselines are compared where supporting evidence exists.

  4. 04

    Select using historical evidence

    Research comparisons assess cuts, holds and hikes separately, examine recent performance and compare alternatives with simple baselines. The selected CPI output can come from a local, global or persistence forecast. Historical relationship strength alone does not select a winning forecast.

  5. 05

    Publish an inspectable snapshot

    Country pages show the issued forecast, its horizon, available probabilities and evidence. The library exposes charts, tables and downloads. Missing outputs remain visible. Forecast snapshots need an explicit import and publication; a calendar refresh does not retrain the models.

POLICY RATES

Direction and size are different questions

The direction-focused model issues a cut, hold or hike outlook and a rate estimate. A separate size model assigns probabilities to 11 outcomes: hold, four named cut sizes, four hike sizes, and other cuts or hikes.

The most likely size category can differ from the point forecast. Probabilities are raw and uncalibrated, so a displayed 70% is not an established 70% success frequency.

MACRO FORECASTS

Inflation and employment over time

Local CPI, PPI and unemployment forecasts cover 1, 2, 3 and 6 months. Each output retains its candidate model and input date. The selected CPI comparison uses historical validation to choose among local, global and persistence predictions.

Intervals from a raw global candidate do not describe a different, selected forecast. Dashed chart lines connect forecast endpoints; they do not predict the path between them.

GLOBAL RELATIONSHIPS

Explore associations across economies

Relationship charts compare historical changes in national inflation and unique monetary-authority rate series. They show the sign and strength of a lagged association alongside the number of paired months.

Correlation does not establish causation, model feature importance or predictive value. These networks are descriptive research, and the raw global rate experiment remains unpreferred.

Explore inflation relationships ↗
PERFORMANCE

Read the score with its denominator

Balanced accuracy averages recall for cuts, holds and hikes. This prevents frequent holds from dominating the headline as much as ordinary accuracy. Country scores share evidence when they share a monetary authority.

Current historical benchmarks concern next-month direction. They do not validate the two-month live outlook. Magnitude errors in the country evidence ledger describe the zero-change persistence comparator.

Inspect model comparisons ↗

Read a forecast in four steps

  1. Check the instrument and dates. A month-end benchmark forecast can span several meetings; 25 basis points means 0.25 percentage points.
  2. Separate the estimate from the scenarios. The point estimate and size probabilities answer different questions.
  3. Inspect the supporting history. Check sample size, recent performance, input freshness and source coverage.
  4. Keep uncertainty in view. Missing data, revised histories and uncalibrated probabilities limit what can be concluded.
Explore country predictions ↗

What “1.0” means. This names the Coldstreet model hub and its current research edition, powered by the supplied Global Macro Engine outputs. It is not evidence of a newly trained or independently validated model. Historical development periods were reused, verified point-in-time vintages are incomplete, and the worldwide 90% accuracy goal remains unmet.