Abstract:Demand for many products may depend on the price of a tradable asset or on the economy in general. For example, demand for equipment that plants or harvests corn correlates with the corn price on the commodity market, and discount stores experienced increased sales revenue during the last recession. Thus, we model demand as a stochastic process with two components: in addition to the usual Gaussian component reflecting demand volatility, there is a drift component taking the form of a function of a tradable as… Show more
“…A commonly studied risk measure is the variance of the profit (see, e.g., Chiu and Choi 2016, Ridder et al 1998, Rubio-Herreroa et al 2015, Wang and Yao 2017, that is M 2 ðyÞ. Zhang et al (2020b) analyze the skewness (i.e., the third moment M 3 ðyÞ) and the kurtosis (i.e., the fourth moment M 4 ðyÞ).…”
Section: Instead Of Focusing On the Expected Profit E[w(y)]mentioning
U ncertainties involved in decision making often impose challenges to our ability of modeling and analyzing the reality. The purpose of this study is to demonstrate how one can go beyond the conventional optimization thinking, via taking a stochastic viewpoint, to push the boundaries of the analysis. We review the basic notions of stochastic orders and stochastic functions, with which the conventional (deterministic) way of modeling can be generalized. Based on the orders among distribution functions associated with random variables, we can treat the input-output relationship as stochastic functions in our models. This viewpoint, leads to extended functional properties in the stochastic sense. Taking the existing models involving inventory and pricing decisions, we show how the stochastic notions are powerful in simplifying and generalizing the analysis, as well as generating new insights.
“…A commonly studied risk measure is the variance of the profit (see, e.g., Chiu and Choi 2016, Ridder et al 1998, Rubio-Herreroa et al 2015, Wang and Yao 2017, that is M 2 ðyÞ. Zhang et al (2020b) analyze the skewness (i.e., the third moment M 3 ðyÞ) and the kurtosis (i.e., the fourth moment M 4 ðyÞ).…”
Section: Instead Of Focusing On the Expected Profit E[w(y)]mentioning
U ncertainties involved in decision making often impose challenges to our ability of modeling and analyzing the reality. The purpose of this study is to demonstrate how one can go beyond the conventional optimization thinking, via taking a stochastic viewpoint, to push the boundaries of the analysis. We review the basic notions of stochastic orders and stochastic functions, with which the conventional (deterministic) way of modeling can be generalized. Based on the orders among distribution functions associated with random variables, we can treat the input-output relationship as stochastic functions in our models. This viewpoint, leads to extended functional properties in the stochastic sense. Taking the existing models involving inventory and pricing decisions, we show how the stochastic notions are powerful in simplifying and generalizing the analysis, as well as generating new insights.
“…Next, we review papers that relate to ours in that demand uncertainty is partly linked to financial assets and thus induces risk hedging strategy. In a recent work, Wang and Yao (2017), production planning with risk hedging is studied in a single-product setting, with the demand depending on a single financial asset. The need to extend to multiple products and multiple financial assets has been motivated above through practical business cases.…”
Section: Literature Reviewmentioning
confidence: 99%
“…The following lemma is essentially the highdimensional version of Lemma 4 in Wang and Yao (2017) and can be easily verified by applying It ô's Lemma and using the admissibility conditions in Equations (A2) and (A15); hence, the proof is omitted. LEMMA A1.…”
Section: Conclusion and Remarksmentioning
confidence: 99%
“…Properties of Itô's integral ( in our case), guarantee that the total hedging wealth from this discretized implementation converges (in L 2 ) to its theoretical value in continuous time (i.e., χ T ) as the implementation frequency increases. Wang and Yao (2017) numerically show that not so frequent update (e.g., monthly) of the hedging position generates a performance quite close to that from daily updates. Of course, how frequent the updates of hedging need depends on specific applications and is limited by available demand update frequency, and the firm should conduct extensive analysis (by simulation, for instance) to see if our model can achieve a performance close to the theoretical value.…”
Section: Numerical Examplesmentioning
confidence: 99%
“…This extension also leads to significant technical difficulties and several new insights as we shall illustrate in the sections below. The work of Wang and Yao (2017) was motivated by Caldentey and Haugh (2006), the latter also considers a single product with a more general production model but with a less explicit solution, and it makes no attempt to characterize the efficient frontier.…”
We study production planning in a multi‐product setting, in which demand for each product depends on multiple financial assets (such as commodities, market indices, etc). In addition to the production quantity decision at the beginning of the planning horizon, there is also a real‐time hedging decision throughout the horizon; and we optimize both decisions jointly. With a mean–variance problem formulation, we first derive the optimal hedging strategy, given the production quantities. This leads to an explicit objective function with which bounds on optimal production quantities are identified. Thus, optimization of the production policies can be readily solved numerically as a static minimization problem. This way, we are able to give a complete characterization of the mean–variance efficient frontier, and quantify the contribution of the hedging strategy by the variance reduction it achieves. Furthermore, the model and results are extended to allow dynamic production control that tracks the demand rates.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.