-
作者：Zednik, Anita
作者单位：Vienna University of Economics & Business
摘要：Most school choice matching mechanisms employed in theory and practice assume that schools rank students by characteristics that cannot be manipulated. However, parents may have incentives to misstate information used for determining school priorities, such as the proximity of the residential address to a school, particularly when such misrepresentations are difficult to detect or carry minimal penalties. If manipulation of school priorities occurs, the efficiency and fairness of the matching ...
-
作者：Jansen, Mark; Kruger, Samuel; Maturana, Gonzalo
作者单位：Utah System of Higher Education; University of Utah; University of Texas System; University of Texas Austin; Emory University
摘要：Do dealers use their financing discretion to charge higher interest rate markups to high-risk customers? We use unique transaction-level data to examine finance and vehicle profits in the subprime auto market with three main results. First, financing subprime customers is costly for dealerships because of loan discounts that are only partially offset by proceeds from interest rate markups. Second, financing is costliest to dealers for deep subprime customers with low credit scores and low inco...
-
作者：Liu, Keqin
作者单位：Xi'an Jiaotong-Liverpool University
摘要：This paper addresses an important class of restless multiarmed bandit (RMAB) problems that finds broad application in operations research, stochastic optimization, and reinforcement learning. There are N independent Markov processes that may be operated, observed and offer rewards. Due to the resource constraint, we can only choose a subset of M (M < N) processes to operate and accrue reward determined by the states of selected processes. We formulate the problem as a partially observable RMAB...
-
作者：Simester, Duncan; Timoshenko, Artem; Zoumpoulis, Spyros I.
作者单位：Massachusetts Institute of Technology (MIT); Northwestern University; INSEAD Business School
摘要：We propose an approach for determining the sample size required when using an experiment to train and certify a targeting policy. Calculating the rate at which the performance of a targeting model improves with additional training data is a complex problem. We address this challenge by assuming that customers are grouped into segments that capture relevant information about their responsiveness to the firm's marketing actions. We consider two problem formulations. The first formulation identif...
-
作者：Simchi-Levi, David; Zheng, Zeyu; Zhu, Feng
作者单位：Massachusetts Institute of Technology (MIT); University of California System; University of California Berkeley
摘要：We build a unified modeling framework for classical online matching problems and emerging online matching problems with three additional practical features: reusable resources, network resources, and decaying rewards. For online matching problems in the unified framework, we provide a unified performance analysis tool for the greedy policy and its simple variants, which we refer to as greedy-like policies. We prove that greedylike policies can achieve near-optimal performances for online match...
-
作者：Gao, Long; Jian, Dawei; Gumus, Mehmet; Mishra, Birendra K.
作者单位：University of California System; University of California Riverside; University of Wisconsin System; University of Wisconsin Milwaukee; McGill University
摘要：Demand externalities arise when past sales stimulate future demand. They pervade many consumer markets. To penetrate such markets, how should manufacturers contract with retailers? We formulate the problem as a dynamic game, wherein the retailer can privately observe and control evolving market conditions, and consumers can act either myopically or strategically. Our contribution is threefold. (i) We characterize the optimal contract: It resolves a dynamic tradeoff between exploiting demand ex...
