Mail-Order Demands for Style Goods: Theory and Data Analysis

Abstract

Arguments are presented which result in the following candidates for data-generating processes:(1) ratios of successive forecasts are distributed lognormally; (2) ratios of successive forecasts are distributed as t_ (Student); (3) actual demands during unequal time periods are distributed as negative binomial. Analysis of the data suggests the negative binomial data-generating process as both most closely representing the underlying process and being simple to adapt to a decision model. The paper concludes with an example of the use of the chosen data-generating process in a decision framework, and deals briefly with some issues of implementation.G3G041

Innovative Quick Response Programs in Logistics and Supply Chain Management

“…Smith and Achabal (1998) present a model that includes both markdown pricing and inventory management and report on its use in three retail chains. Related papers include ; Crowston et al (1973); Hausman and Peterson (1972); Hausman and Sides (1973); and Mantrala and Rao (2001). Raman (1999) presents a review of research on fashion products, classified as production and inventory planning models, pricing and related models, and approaches for parameter estimation (particularly demand forecasts and forecast error estimation).…”

Estimating retail demand with Poisson mixtures and out‐of‐sample likelihood

“…The application of the NB distribution to model demand of goods can be traced back to Hausman and Sides who show that the NB distribution is a nice choice to be incorporated into inventory decision framework. Many years later, Agrawal and Smith rediscover the utility of the NB distribution in estimating retail demand.…”

A Bayesian Approach to the Two-period Style-goods Inventory Problem with Single Replenishment and Heterogeneous Poisson Demands

“…For the augmented NBD, the analogue to (7) is 16 (8) where <fJ is the proportion of posters which have zero expected demand and <Po is the proportion having X 1 = 0. For the x > 0 categories, (7) and (8) are, with appropriate rand IX, equivalent, and (7) need only be modified for the x = 0 category.…”

“…Parameter estimates of r, IX and 4> for the augmented NBD of (8) were obtained using the iterative algorithm suggested by Morrison. 16 This involves solving the following three equations: …”

“…Considering its importance and complexity, it is not surprising that the vast majority of research in this area has focused on the problem of demand forecasting (see, for example, Chang and Fyffe, 4 Goyat,S Green and Harrison, 6 Hausman and Peterson, 7 Hausman and Sides, 8 Hertz and Schaffir, 9 Murray and Silver, 10 Ravindran 11 and Silver 12 ). Considering its importance and complexity, it is not surprising that the vast majority of research in this area has focused on the problem of demand forecasting (see, for example, Chang and Fyffe, 4 Goyat,S Green and Harrison, 6 Hausman and Peterson, 7 Hausman and Sides, 8 Hertz and Schaffir, 9 Murray and Silver, 10 Ravindran 11 and Silver 12 ).…”