Table 1. Team methods, parameter and prediction errors, and overall scores.
Team | Optimization method | Cost function | Reduction strategy | Estimation problem | Parameter error | Prediction error | Score |
---|---|---|---|---|---|---|---|
Crux | Derivative-based | MLE | None | Artificial | 2.60×10−19 | 0.052 | 38.1 |
New Dream | N/R | N/R | N/R | Artificial | 1.39×10−6 | 0.023 | 11.6 |
ICM Poland | Derivative-based | Log ratio (Eq 1) | None | Artificial | 1.75×10−6 | 0.028 | 9.35 |
Alucinatori | Derivative-based | Log ratio (Eq 1) | None | Artificial | 1.14×10−3 | 0.041 | 1.84×10−4 |
Whole-Sale Modelers | Differential evolution | Least squares (Eq 2) | Principal components | True | 3.61×10−3 | 0.111 | 1.40×10−4 |
CU | N/R | N/R | Model reduction | True | 3.56×10−3 | 0.688 | 6.71×10−5 |
Team 9 | N/R | N/R | N/R | True | 3.56×10−3 | 0.711 | 6.61×10−5 |
Hurricane | N/R | N/R | N/R | True | 8.87×10−3 | 0.689 | 2.96×10−5 |
DBI-Guesstimators | N/R | N/R | N/R | True | 8.87×10−3 | 0.689 | 2.96×10−5 |
Uniandes | N/R | N/R | N/R | True |
“Estimation problem” column indicates which teams used the parameter error data. Teams are listed by overall score in descending order. Team Uniandes did not submit a solution and therefore was not scored. Not reported (N/R) indicates teams that did not report their approach.