Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Inventory performance of the damped trend forecasting method

Li, Qinyun and Disney, Stephen 2018. Inventory performance of the damped trend forecasting method. Presented at: 20th International Working Seminar of Production Economics, Innsbruck, Austria, 19 - 23 February 2018.

[img]
Preview
PDF - Submitted Pre-Print Version
Download (286kB) | Preview

Abstract

The Damped Trend (DT) forecasting method has been recognized for its superior accuracy. Li et al., (2014) show when DT forecasts are used within the order-up-to (OUT) policy, the bullwhip effect is avoided by using unconventional DT parameter settings. We extend this study in three directions. First, by investigating the relationship between the stability and invertibility, we show that stable DT parameter sets produce feasible forecasts. This further justifies the choice of unconventional DT parameter values. Second, we extend the bullwhip analysis from a lead-time of one to a general lead-time, identifying a stable and invertible region in the parameter space that possesses enviable bullwhip avoidance behavior. Third, we characterize the frequency response of the inventory levels maintained by the OUT policy with DT forecasts. For independently and identically distributed (i.i.d.) demand the net stock amplification ratio can be close to (but never smaller than) the lead-time and review period, with the intriguing benefit of bullwhip avoidance. For other demand patterns, the net stock amplification can be less than the i.i.d. lower bound. The bullwhip can also be reduced at the same time. Simulations of 62 sets of real demand time series verify our analytical results.

Item Type: Conference or Workshop Item (Paper)
Date Type: Completion
Status: Unpublished
Schools: Business (Including Economics)
Last Modified: 24 Jul 2018 15:16
URI: http://orca.cf.ac.uk/id/eprint/109431

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics