R2CCP Bid Prediction
Multimodal R2CCP forecasting · 8 context models · 500K Monte Carlo decisions
Built with Python · R2CCP · Conformal prediction · Entropy regularization · Monte Carlo simulation
WHY
PQ bids are evaluated by both technical and price scores. As the technical score falls, viable price bands split around invalid regions, so actual bid behavior becomes multimodal rather than forming one central peak. A useful decision system had to preserve those separated regions and estimate the win probability of each candidate rate instead of returning one point or one merged interval.
Chronological train and validation split
90.73% weighted conformal coverage
Group-company PQ bid performance
HOW
Preserve the distribution, then simulate the decision
Context-specific calibration keeps distinct modes separate before simulation evaluates candidate actions.
- 01 Context routing
Combine ranking position Q1/Q2 with four bid-rate-difference quartiles.
- 02 R2CCP distribution
Train eight entropy-regularized context models on a chronological split.
- 03 Per-bin conformal set
Retain only bins above the calibrated threshold and preserve disjoint intervals.
- 04 Monte Carlo decision
Sample competing outcomes 500,000 times and estimate the win probability of each candidate rate.
RESULT
Eight-context chronological validation
| Context | Coverage | Average interval length |
|---|---|---|
| Q1-BRD1 | 91.39% | 0.0149 |
| Q1-BRD2 | 92.23% | 0.0194 |
| Q1-BRD3 | 88.07% | 0.0166 |
| Q1-BRD4 | 91.21% | 0.0169 |
| Q2-BRD1 | 86.14% | 0.0220 |
| Q2-BRD2 | 81.41% | 0.0208 |
| Q2-BRD3 | 93.92% | 0.0285 |
| Q2-BRD4 | 94.77% | 0.0534 |
Weighted coverage: 12,688 / 13,984 = 90.73%.
Contribution
- Diagnosed multimodal interval collapse and rebuilt inference with per-bin conformal thresholds and entropy regularization.
- Designed the eight-context chronological evaluation and connected distribution forecasts to 500,000-iteration candidate simulation used in bid decisions.