Timothy L. Urban

An inventory-theoretic approach to product assortment and shelf-space allocation

Abstract The purpose of this research is to generalize and integrate existing inventory-control models, product assortment models, and shelf-space allocation models. We first generalize the inventory-level-dependent demand inventory model to explicity model the demand rate as a function of the displayed inventory level. We then investigate the product assortment and shelf-space allocation problems by extending this model into the multi-item, constrained environment. A greedy heuristic and a genetic algorithm are proposed for the solution to the integrated problem.

Inventory models with inventory-level-dependent demand: A comprehensive review and unifying theory

Marketing researchers and practitioners have long recognized the demand of many retail items is proportional to the amount of inventory displayed. Recently, two distinct types of inventory control models reflecting this relationship have appeared in the literature, models in which the demand rate of an item is a function of the initial inventory level and those in which it is dependent on the instantaneous inventory level. We present a comprehensive overview of this literature and demonstrate the equivalence of the two types of models through the use of a simple, periodic-review model. An alternative approach to sensitivity analysis for inventory models with inventory-level-dependent demand is also presented.

A neural network approach to mutual fund net asset value forecasting

In this paper, an artificial neural network method is applied to forecast the end-of-year net asset value (NAV) of mutual funds. The back-propagation neural network is identified and explained. Historical economic information is used for the prediction of NAV data. The results of the forecasting are compared to those of traditional econometric techniques (i.e. linear and nonlinear regression analysis), and it is shown that neural networks significantly outperform regression models in situations with limited data availability.

Optimal ordering and pricing policies in a single-period environment with multivariate demand and markdowns

This paper investigates a single-period inventory model in which the demand of the product is a deterministic, multivariate function of price, time, and level of inventory. Models are formulated for the basic pricing case and the case with a price markdown during the season. Solution methodologies are presented for each case when the pricing decisions are predetermined and when they are decision variables. Comments on the practical use of this model are presented, and sensitivity analysis is conducted on the decision variables and demand parameters.

A HEURISTIC FOR THE DYNAMIC FACILITY LAYOUT PROBLEM

This paper presents a heuristic for the dynamic facility layout problem. All existing methods for solving this problem require the use of a dynamic programming model, the optimal solution of the quadratic assignment problem, or both. The proposed heuristic is based on the steepest-descent pairwise-interchange procedure to develop layouts utilizing material handling cost data from varying lengths of forecast windows as well as the explicit consideration of the corresponding rearrangement costs. Numeric results indicate that it typically performs as well as any existing methodology and only slightly worse than optimal.

An optimal piecewise-linear program for the U-line balancing problem with stochastic task times

Abstract The utilization of U-shaped layouts in place of the traditional straight-line configuration has become increasingly popular, with reported benefits of substantial improvements in productivity and quality. This paper examines the U-line balancing problem with stochastic task times. A chance-constrained, piecewise-linear, integer program is formulated to find the optimal solution. Various approaches used to identify a tight lower bound are also presented, as are operable extensions to the basic model. Computational results show that the proposed method is able to solve practical-sized problems.

Deterministic inventory models incorporating marketing decisions

Abstract This paper investigates a finite replenishment inventory model in which the demand of an item is a deterministic function of price and advertising expenditures. The formulated models also incorporate learning effects and the possibility of defective items in the production process. A general solution methodology is developed to determine the optimal lot size, price mark-up, and advertising expenditure simultaneously. This method utilizes separable programming resulting in an effective computer technique to find the global optimal solution. Closed-form solutions are found for special cases.

The stochastic U-line balancing problem: A heuristic procedure

Many heuristics have been proposed for the assembly line balancing problem due to its computational complexity and difficulty in identifying an optimal solution. Still, the basic line balancing model fails to consider a number of realistic elements. The implementation of a Just-In-Time manufacturing system generally entails the replacement of traditional straight assembly lines with U-shaped lines. An important issue in the U-line balancing problem is the consideration of task time variability due to human factors or various disruptions. In this paper, we consider the stochastic U-line balancing problem. A hybrid heuristic is presented consisting of an initial feasible solution module and a solution improvement module. To gain insight into its performance, we analyze the heuristic under different scenarios of task time variability. Computational results clearly demonstrate the efficiency and robustness of our algorithm.

THE INTEGRATED MACHINE ALLOCATION AND LAYOUT PROBLEM

Cellular manufacturing has received a considerable amount of attention in the research literature as an approach for improving the performance of manufacturing facilities. However, recent studies have shown that cellular layouts are not always superior to the traditional functional machine layout. We propose a model that does not require the machines to be placed in a functional layout or in a cellular arrangement, but allows the material flow requirements to dictate the machine placement. The model is formulated as an aggregation of the quadratic assignment problem and several network flow problems coupled with linear side constraints. A mixed integer program is presented to find the optimal solution for small problems, and heuristics are developed to solve larger problems. Computational results evaluating the quality of the solution methodologies are also presented.

Inventory models with the demand rate dependent on stock and shortage levels

This paper investigates an inventory system in which the demand rate during stockout periods differs from that during the in-stock period by a given amount. The previous analysis conducted in this area formulated the model as a cost-minimization model. This type of formulation will intentionally try to decrease demand, by increasing the stockout period, in order to decrease costs. This paper appropriately considers the model as a profit-maximization model and develops a closed-form solution. The model is then further generalized to incorporate the effect of stock-level-dependent demand rates and considers initial-stock-dependent demand as well as instantaneous-stock-dependent demand rates.