|
|
|
|
LEADER |
02526nam a2200373Ia 4500 |
001 |
10.1287-mnsc.2021.4071 |
008 |
220706s2022 CNT 000 0 und d |
020 |
|
|
|a 00251909 (ISSN)
|
245 |
1 |
0 |
|a Meta Dynamic Pricing: Transfer Learning Across Experiments
|
260 |
|
0 |
|b INFORMS Inst.for Operations Res.and the Management Sciences
|c 2022
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.1287/mnsc.2021.4071
|
520 |
3 |
|
|a We study the problem of learning shared structure across a sequence of dynamic pricing experiments for related products. We consider a practical formulation in which the unknown demand parameters for each product come from an unknown distribution (pri- or) that is shared across products. We then propose a meta dynamic pricing algorithm that learns this prior online while solving a sequence of Thompson sampling pricing experiments (each with horizon T) for N different products. Our algorithm addresses two challenges: (i) balancing the need to learn the prior (meta-exploration) with the need to leverage the estimated prior to achieve good performance (meta-exploitation) and (ii) accounting for uncertainty in the estimated prior by appropriately “widening” the estimated prior as a function of its estimation error. We introduce a novel prior alignment technique to analyze the regret of Thompson sampling with a misspecified prior, which may be of independent interest. Unlike prior-independent approaches, our algorithm’s meta regret grows sublinearly in N, demonstrating that the price of an unknown prior in Thompson sampling can be negligible in experiment-rich environments (large N). Numerical experiments on synthetic and real auto loan data demonstrate that our algorithm significantly speeds up learning compared with prior-independent algorithms. Copyright: © 2021 INFORMS
|
650 |
0 |
4 |
|a Costs
|
650 |
0 |
4 |
|a Dynamic pricing
|
650 |
0 |
4 |
|a empirical Bayes
|
650 |
0 |
4 |
|a Empirical Bayes
|
650 |
0 |
4 |
|a Learn+
|
650 |
0 |
4 |
|a Learning algorithms
|
650 |
0 |
4 |
|a meta learning
|
650 |
0 |
4 |
|a Metalearning
|
650 |
0 |
4 |
|a misspecified prior
|
650 |
0 |
4 |
|a Misspecified prior
|
650 |
0 |
4 |
|a Pricing experiments
|
650 |
0 |
4 |
|a Related products
|
650 |
0 |
4 |
|a Shared structures
|
650 |
0 |
4 |
|a Thompson sampling
|
650 |
0 |
4 |
|a Thompson samplings
|
650 |
0 |
4 |
|a transfer learning
|
650 |
0 |
4 |
|a Transfer learning
|
650 |
0 |
4 |
|a Uncertainty analysis
|
700 |
1 |
|
|a Bastani, H.
|e author
|
700 |
1 |
|
|a Simchi-Levi, D.
|e author
|
700 |
1 |
|
|a Zhu, R.
|e author
|
773 |
|
|
|t Management Science
|