Moriarno Ratings — Predictive Risk Ratings for Japanese IP

Current Forecasts

Upcoming Titles — Awaiting Release

Each title is evaluated by three independent models. Grades reflect the probability of not reaching the Netflix Global Top 10. Performance estimates show expected viewership hours weighted by each model's success probability.

Viral Hit

If enters Top 10: ~24.4M hours Strong

Model A

Content + Actor + Studio

Aaa

11.9% failure probability

Expected hours 21.5M Strong

Model B

Actor + Studio + Broadcaster

Baa

57.4% failure probability

Expected hours 10.4M Moderate

Model C

Tags + Actor + Studio + BC

Aaa

18.2% failure probability

Expected hours 20.0M Strong

Actual Result

Awaiting Release

Sins of Kujo

If enters Top 10: ~10.4M hours Moderate

Model A

Content + Actor + Studio

Aa

27.8% failure probability

Expected hours 7.5M Brief

Model B

Actor + Studio + Broadcaster

B

91.4% failure probability

Expected hours 0.9M Brief

Model C

Tags + Actor + Studio + BC

B

90.1% failure probability

Expected hours 1.0M Brief

Actual Result

Awaiting Release

Soul Mate

If enters Top 10: ~16.2M hours Moderate

Model A

Content + Actor + Studio

A

43.1% failure probability

Expected hours 9.2M Moderate

Model B

Actor + Studio + Broadcaster

Aa

23.8% failure probability

Expected hours 12.4M Moderate

Model C

Tags + Actor + Studio + BC

Ba

78.1% failure probability

Expected hours 3.5M Brief

Actual Result

Awaiting Release

Straight to Hell

If enters Top 10: ~16.2M hours Moderate

Model A

Content + Actor + Studio

Baa

61.0% failure probability

Expected hours 6.3M Brief

Model B

Actor + Studio + Broadcaster

Aa

21.1% failure probability

Expected hours 12.8M Moderate

Model C

Tags + Actor + Studio + BC

Aaa

11.1% failure probability

Expected hours 14.4M Moderate

Actual Result

Awaiting Release

Failure Probability

Probability of not reaching Netflix Global Top 10. Lower = better.

Expected Hours

P(success) × predicted hours if G10 entry. Combines likelihood with magnitude.

Performance Tiers

Mega 50M+ Strong 20–50M Moderate 8–20M Brief <8M

Performance Model

R²=0.26, based on content features (survival, action, series format, workplace).

Model Validation

Cross-Validation & Temporal Stability

All models are validated through rigorous cross-validation on historical Netflix Global Top 10 data (2021–2026). Model B achieves 0.86 AUC in stratified 5-fold cross-validation (±0.008) and maintains performance across temporal splits—predictions trained on 2021–2024 data accurately rank 2025–2026 titles (AUC 0.857–0.881).

Model A

0.868

LOOCV AUC · 96 titles

Model B

0.861

5-Fold CV · 127 titles · ±0.008

Model C

0.834

LOOCV AUC · 127 titles

Forecast History

v4.0 — Archived

Title	Grade	Model	Issued
Viral Hit	Aaa	v4.0	2026-03-18
Soul Mate	Aaa	v4.0	2026-03-18
Sins of Kujo	Aaa	v4.0	2026-03-18
Straight to Hell	Aa	v4.0	2026-03-18

Historical forecasts are preserved as issued. Numbers reflect the model version at time of publication. Original grades shown in current Moody's scale.

Methodology

How Ratings Are Produced

Ratings are generated by proprietary multi-factor models trained on the complete census of Netflix Japan Global titles (2020–2025). Each model evaluates a different combination of content characteristics, talent history, production track record, and source material to estimate the probability of reaching the Netflix Global Top 10. Titles receive grades from Aaa (highest) to B (lowest) based on calibrated probability thresholds. All ratings are validated through cross-validation against historical outcomes.

Forecast Immutability

Published forecasts are never retroactively changed. Each forecast is tied to a model version and issue date. New model versions generate new forecasts; previous forecasts remain on record. When actual results come in, we verify against the original published forecast — not a recalculated number.