Research On Model And Solution For Data-driven Newsboy Problem With Price-Sensitive Demand

In recent years,with the development of data,data information has become the fourth strategic resource besides human,financial and material resources.Data drive making decision in supply chain can effectively improve the efficiency of supply chain operation and reduce operating costs.More and more enterprises need the ability to apply the information obtained from data analysis to enterprise decision-making.How to excavate useful knowledge to support senior management decision-making through deep processing and processing from a large amount of data resources accumulated by enterprises is an area that academia attaches great importance to.Different from the traditional supply chain management research,data-driven supply chain management puts forward higher requirements for data modeling and optimization methods.In the face of data flow,how to adopt appropriate models and adopt appropriate methods to improve the ability of decision makers to respond quickly will be an important challenge.Therefore,the refined operation of supply chain driven by data is the main direction of future research in the field of supply chain.In this paper,two kinds of newsboy problems which are widely used in practice,such as the newsboy problem without price-sensitive demand and the newsboy pricing problem with price sensitive demand.The truncated data-driven method and the sample average approximation method under the data-driven method are used.The main research work of this paper is as follows:(1)On the basis of a systematic review of relevant literature on data-driven and Newsboy problem,the corresponding concepts and theoretical analysis are given,including two Newsboy problems with exogenous prices,Newsboy pricing problems with price-sensitive demand,sample average approximate data-driven methods,and the application of truncated data-driven methods.(2)Based on the actual background of unknown market demand distribution,two data-driven Newsboy models,risk neutral and risk aversion,are constructed considering exogenous prices.Secondly,the numerical relationship between risk aversion parameters,data volume,accuracy and confidence of the two data-driven Newsboy models is deeply explored.Finally,the accuracy of the data-driven model is compared with that of the other two mainstream methods through numerical experiments,which verifies the validity of the model in different situations.(3)Based on the existing research results,a data-driven newsboy model with price-dependent demand is constructed and solved.Then the theoretical relationship between the accuracy of the data-driven solution and the data quantity and confidence is explored by establishing a regret function.Finally,a numerical experiment is carried out.The validity and accuracy of the model are verified.The sensitivity of data-driven pricing newsboy model to different parameters and the adaptability of data-driven pricing newsboy model with different distribution function types are analyzed.In summary,this paper proposes a data-driven newsboy model with profit maximization as the goal,and constructs two Newsboy models with exogenous price and a newsboy pricing model with demand changing with price.This model enriches the relevant theory of newsboy model research,and also enriches other single decision variables and double decision variables.The research of data driven model and data quantity provides some references.