-
作者：Modaresi, Sajad; Saure, Denis; Vielma, Juan Pablo
作者单位：University of North Carolina; University of North Carolina Chapel Hill; Universidad de Chile; Massachusetts Institute of Technology (MIT)
摘要：We study dynamic decision making under uncertainty when, at each period, a decision maker implements a solution to a combinatorial optimization problem. The objective coefficient vectors of said problem, which are unobserved before implementation, vary from period to period. These vectors, however, are known to be random draws from an initially unknown distribution with known range. By implementing different solutions, the decision maker extracts information about the underlying distribution b...
-
作者：Hazimeh, Hussein; Mazumder, Rahul
作者单位：Massachusetts Institute of Technology (MIT); Massachusetts Institute of Technology (MIT)
摘要：The L-0-regularized least squares problem (a.k.a. best subsets) is central to sparse statistical learning and has attracted significant attention across the wider statistics, machine learning, and optimization communities. Recent work has shown that modern mixed integer optimization (MIO) solvers can be used to address small to moderate instances of this problem. In spite of the usefulness of L-0-based estimators and generic MIO solvers, there is a steep computational price to pay when compare...
-
作者：Misic, Velibor V.
作者单位：University of California System; University of California Los Angeles
摘要：Tree ensemble models such as random forests and boosted trees are among the most widely used and practically successful predictive models in applied machine learning and business analytics. Although such models have been used to make predictions based on exogenous, uncontrollable independent variables, they are increasingly being used to make predictions where the independent variables are controllable and are also decision variables. In this paper, we study the problem of tree ensemble optimi...
-
作者：Baillon, Aurelien; Bleichrodt, Han; Emirmahmutoglu, Aysil; Jaspersen, Johannes; Peter, Richard
作者单位：Erasmus University Rotterdam; Erasmus University Rotterdam - Excl Erasmus MC; Australian National University; Norwegian School of Economics (NHH); University of Munich; University of Iowa
摘要：Personal decisions about health hazards are the main cause of impaired health and premature death. People smoke and eat too much, and they exercise too little. The lack of preventive efforts is surprising given their proven effectiveness. In the early 1960s, Arrow suggested that moral hazard might be a reason for underprevention, but this explanation was later challenged. In this paper, we show that underprevention might be caused by misperceived probabilities. We derive when and how probabili...
-
作者：Cai, Ning; Zhang, Wei
作者单位：Hong Kong University of Science & Technology
摘要：For traditional perpetual American put options under regime-switching models, the risk-free interest rates are typically assumed to be positive, and optimal stopping usually can occur in any regime. However, this may not hold true when the risk-free interest rates are allowed to be equal to zero (the interest rate may drop to zero in reality, e.g., in certain periods in Japan); there may exist continuation regimes within which optimal stopping can never occur, that is, within which stopping is...
-
作者：Pedraza-Martinez, Alfonso J.; Hasija, Sameer; Van Wassenhove, Luk N.
作者单位：Indiana University System; IU Kelley School of Business; Indiana University Bloomington; INSEAD Business School; INSEAD Business School
摘要：We study incentive alignment for the coordination of humanitarian operations. Transportation is the second-largest overhead cost (after personnel) for international humanitarian organizations (IHOs). Yet, the management of IHO vehicle fleets faces obstacles to reach efficiency, due to a structural conflict between the incentives of an IHO's individual program (which prioritize prompt service and minimal program cost) and the IHO's central headquarters (which on top of the objective of the prog...
-
作者：Bansal, Saurabh; Dyer, James S.
作者单位：Pennsylvania Commonwealth System of Higher Education (PCSHE); Pennsylvania State University; Pennsylvania State University - University Park; University of Texas System; University of Texas Austin
摘要：In this paper, we consider the problem in which a firm offers a portfolio of products (agricultural seeds) to multiple customer segments comprising farmers under aggressive fill-rate constraints, and some, but not all, customers will accept a substitute to their preferred choice. This business situation is not adequately represented by traditional inventory-management models, where a firm initiates a substitution based on its monetary considerations. By exploiting some recent results on polyhe...
-
作者：Kallus, Nathan; Udell, Madeleine
作者单位：Cornell University
摘要：We study the problem of dynamic assortment personalization with large, heterogeneous populations and wide arrays of products, and demonstrate the importance of structural priors for effective, efficient large-scale personalization. Assortment personalization is the problem of choosing, for each individual (type), a best assortment of products, ads, or other offerings (items) so as to maximize revenue. This problem is central to revenue management in e-commerce and online advertising where both...
-
作者：Lobel, Ilan
作者单位：New York University
摘要：We consider the problem of dynamic pricing in the presence of patient consumers. We call a consumer patient if she is willing to wait a certain number of periods for a lower price and will purchase as soon as the price is equal to or below her valuation. We allow for arbitrary joint distributions of patience levels and valuations. We propose an efficient dynamic programming algorithm for finding optimal pricing policies. We find numerically that optimal policies can take the form of incomplete...
-
作者：Xuan Vinh Doan; Tri-Dung Nguyen
作者单位：University of Warwick; University of Southampton
摘要：In classical newsvendor games, vendors collaborate to serve their aggregate demand whose joint distribution is assumed known with certainty. We investigate a new class of newsvendor games with ambiguity in the joint demand distributions, which is represented by a Frechet class of distributions with some, possibly overlapping, marginal information. To model this new class of games, we use ideas from distributionally robust optimization to handle distributional ambiguity and study the robust new...
