产品管理系统的设计与实现——浅谈从CRM到“X”RM转变的必然

随着通信和互联网技术的发展,对于新兴的销售服务行业来说,CRM其实意味着＂X＂RM,它不再是传统意义上的客户关系管理,而是细分为产品、市场、销售、服务等越来越多的模块,范畴更加广泛,客户的定义越来越大,关系也越来越复杂。＂以客户为中心＂这句看似口号的真理,不得不转化为竞争力,落在实处。本文结合综合产品管理系统的设计与实现过程来阐述销售服务行业的CRM应随着业务和管理的需求与时俱进的必要性。     

Extensions to emergency vehicle location models

This paper is concerned with extending models for the maximal covering location problem in two ways. First, the usual 0–1 coverage definition is replaced by the probability of covering a demand within the target time. Second, once the locations are determined, the minimum number of vehicles at each location that satisfies the required performance levels is determined. Thus, the problem of identifying the optimal locations of a pre-specified number of emergency medical service stations is addressed by goal programming. The first goal is to locate these stations so that the maximum expected demand can be reached within a pre-specified target time. Then, the second goal is to ensure that any demand arising located within the service area of the station will find at least one vehicle, such as an ambulance, available. Erlang's loss formula is used to identify the arrival rates when it is necessary to add an ambulance in order to maintain the performance level for the availability of ambulances. The model developed has been used to evaluate locations for the Saudi Arabian Red Crescent Society, Riyadh City, Saudi Arabia.     

Due-date assignment for multi-server multi-stage assembly systems

In this paper, we attempt to present a constant due-date assignment policy in a multi-server multi-stage assembly system. This system is modelled as a queuing network, where new product orders are entered into the system according to a Poisson process. It is assumed that only one type of product is produced by the production system and multi-servers can be settled in each service station. Each operation of every work is operated at a devoted service station with only one of the servers located at a node of the network based on first come, first served (FCFS) discipline, while the processing times are independent random variables with exponential distributions. It is also assumed that the transport times between each pair of service stations are independent random variables with generalised Erlang distributions. Each product's end result has a penalty cost that is some linear function of its due date and its actual lead time. The due date is calculated by adding a constant to the time that the order enters into the system. Indeed, this constant value is decided at the beginning of the time horizon and is the constant lead time that a product might expect between the time of placing the order and the time of delivery. For computing the due date, we first convert the queuing network into a stochastic network with exponentially distributed arc lengths. Then, by constructing an appropriate finite-state continuous-time Markov model, a system of differential equations is created to find the manufacturing lead-time distribution for any particular product, analytically. Finally, the constant due date for delivery time is obtained by using a linear function of its due date and minimising the expected aggregate cost per product.     

Estimating the efficiency of Portuguese hospitals using an appropriate production technology

This paper investigates the production technology of Portuguese hospitals using various statistical tests and highlights the importance of technology assessment before efficiency estimates are done. Two different models were considered, one based on monetary units and another on quantities for a 4‐year period (2005–2008). An analysis involving all observations (all years) simultaneously led to the conclusion that the technologies of the Portuguese hospitals are globally nonincreasing returns to scale for a confidence interval of 95%. Based on this technology, we found significant inefficiency levels in the Portuguese hospitals. We also concluded that most groups of hospitals had improvements in the studied period and, on average, both models prove that single hospitals and those located in the North were the most efficient. An analysis of returns to scale seems to indicate that hospitals should reach an optimal scale by reducing their cost levels and increasing their assets.     

Knowledge representations for the interactive selling of financial services

Selling financial services requires deep knowledge about the product domain as well as about potential wishes and needs of customers. In the financial services domain (especially in the retail sector) sales representatives can differ greatly in their expertise and level of sales knowledge. Therefore financial service providers ask for tools effectively supporting sales representatives in the dialog with the customer. In this paper we present technologies which allow a flexible mapping of product, marketing and sales knowledge to the representation of a recommender knowledge-base thus providing an infrastructure for the interactive selling of financial services. Furthermore, we report experiences gained from financial service recommender development projects.

A hierarchical model of the impact of RFID practices on retail supply chain performance

The primary purpose of this study was to evaluate the impact of radio frequency identification (RFID) practices on supply chain performance. We examined eight variables of RFID applications grouped in two categories: location (supplier’s warehouse, retailer’s central warehouse, retailer’s local warehouse, retailer’s owned stores) and utilisation (standards, transportation, pallet level, specialised software). Given the inherent difficulty in assessing supply chain performance and the widespread use of different performance models, such as the SCOR and balanced scorecard, we developed a list of performance indicators. Factor analysis produced 7 supply chain performance factors: supplier, inventory, distribution, ordering, plan, sales, and forecasting.Empirical data were collected via an online survey administered to 300 retail companies. 130 usable questionnaires were returned, for a 43.3% response rate. To the best of our knowledge, this is the first study to provide an analytical model that places supply chain performance indicators as dependent variables in a hierarchical regression equation with RFID variables as independent variables. Results found that the implementation of RFID practices significantly affect the supply chain performance in the following areas: supplier, inventory, distribution, plan, sales, and forecasting. RFID can improve the performance of distribution systems, including products dispatched and inventory in transit by 33.8% and stock availability by 45.6%. This study contributes to both the RFID and the supply chain performance literatures. Limitations and suggestions for further research are also discussed.     

Hierarchical maximal-coverage location–allocation: Case of generalized search-and-rescue

We offer a variant of the maximal covering location problem to locate up to p$p$ signal-receiving stations. The “demands,” called geolocations, to be covered by these stations are distress signals and/or transmissions from any targets. The problem is complicated by several factors. First, to find a signal location, the signal must be received by at least three stations—two lines of bearing for triangulation and a third for accuracy. Second, signal frequencies vary by source and the included stations do not necessarily receive all frequencies. One must decide which listening frequencies are allocated to which stations. Finally, the range or coverage area of a station varies stochastically because of meteorological conditions. This problem is modeled using a multiobjective (or multicriteria) linear integer program (MOLIP), which is an approximation of a highly nonlinear integer program. As a solution algorithm, the MOLIP is converted to a two-stage network-flow formulation that reduces the number of explicitly enumerated integer variables. Non-inferior solutions of the MOLIP are evaluated by a value function, which identifies solutions that are similar to the more accurate nonlinear model. In all case studies, the “best” non-inferior solutions were about one to four standard deviations better than the sample mean of thousands of randomly located receivers with heuristic frequency assignments. We also show that a two-stage network-flow algorithm is a practical solution to an intractable nonlinear integer model. Most importantly, the procedure has been implemented in the field.     

The growth of service and the service of growth: Using system dynamics to understand service quality and capital allocation

This paper discusses how system dynamics can help understand a service company's growth potential as well as its limitations. The model discussed here is being built for a European restaurant chain which grew from nothing to over 200 outlets in less than a decade. The model highlights two conflicting pressures: the need to spend on meeting customer expectations and hence build sales versus the need to meet profit targets from headquarters and thus win the capital to fund expansion. We use the model to study how management policies affect the achievable rate of growth. The issues discussed are relevant to any service based company facing the problem of maintaining and improving service quality against the pressure of performance expectations set by shareholders or corporate owners. We also briefly discuss the benefit of using such models for executive training. The model will be used as a basis for educating the emerging generation of managers who will have to cope with the tensions described in the model.     

基于聚类与机器学习的零售商品销量预测

本文提出一种基于K-means聚类与机器学习回归算法的预测模型以解决零售行业多个商品的销售预测问题,首先通过聚类分析识别出具有相似销售模式的商品从而实现数据集的划分,然后分别在每个子数据集上训练了支持向量回归、随机森林以及XGBoost模型,通过构建数据池的方式增加了用于训练模型的数据量以及预测变量的选择范围.在一家零售企业的真实销售数据集上对提出的模型进行了验证,实验结果表明基于K-means和支持向量回归的预测模型表现最优,且所提出的模型预测效果明显优于基准模型以及不使用聚类的机器学习模型.     

Synthesis of control policies for manufacturing systems using eigenvalue-assignment techniques †

In this paper, eigenvalue–assignment techniques are used to synthesize control policies for a manufacturing system. This system is modelled as a diserete–time multivariate dynamical system with a disturbance input duo to sales. The state variables of the system are the rotes of flow of parts at the various work stations, the backlogs of parts, and the inventory level of the finished product. The control inputs ore the man–hours–per–week required for the various work processes involved in the manufacturing system.