Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain Performance

This study presents the results of an investigation into effectiveness of one-step and multi-step (h-step-ahead) forecasting methods in mitigating the Bullwhip Effect and improving supply chain performance within an order-up-to-level inventory control system. the Bullwhip Effect, a phenomenon in whi...

Full description

Saved in:
Bibliographic Details
Main Authors: Alper Saricioglu, Mujde Erol Genevois, Michele Cedolin
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10772207/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846123640239685632
author Alper Saricioglu
Mujde Erol Genevois
Michele Cedolin
author_facet Alper Saricioglu
Mujde Erol Genevois
Michele Cedolin
author_sort Alper Saricioglu
collection DOAJ
description This study presents the results of an investigation into effectiveness of one-step and multi-step (h-step-ahead) forecasting methods in mitigating the Bullwhip Effect and improving supply chain performance within an order-up-to-level inventory control system. the Bullwhip Effect, a phenomenon in which small variations in consumer demand cause increasingly larger fluctuations upstream in the supply chain, presents significant challenges for inventory management and cost control. Traditional forecasting methods, such as Moving Average and Exponential Smoothing, have been extensively studied for their impact on supply chain performance. This study is among the first to introduce machine learning forecasting models, specifically Long Short-Term Memory and LightGBM, within this research domain, comparing their performance under various demand conditions, including autoregressive processes with and without seasonality, as well as the well-known M5 forecasting competition dataset. The results reveal that the multi-step-ahead forecasting capability of Long Short-Term Memory and LightGBM significantly outperforms one-step-ahead forecasting in reducing demand amplification, leading to improvements in key supply chain metrics such as order fulfillment rate, variance of inventory, and average end inventory across all autoregressive and M5 series. The findings demonstrate the superior accuracy and stability of machine-learning methods, particularly in scenarios with high demand autocorrelation, seasonality, and variability. These results provide new insights into the potential of advanced forecasting techniques to better manage supply chain variability and reduce the Bullwhip Effect, thereby offering valuable guidance for optimizing inventory control strategies.
format Article
id doaj-art-91a190f5347040aebb4abd2a40bcd23a
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-91a190f5347040aebb4abd2a40bcd23a2024-12-14T00:02:01ZengIEEEIEEE Access2169-35362024-01-011218016118017410.1109/ACCESS.2024.351017510772207Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain PerformanceAlper Saricioglu0https://orcid.org/0000-0002-4015-7200Mujde Erol Genevois1https://orcid.org/0000-0001-5324-0612Michele Cedolin2https://orcid.org/0000-0003-2397-0010Graduate School of Science and Engineering, Galatasaray University, Istanbul, TürkiyeFaculty of Engineering and Technology, Galatasaray University, Istanbul, TürkiyeCollege of Engineering and Technology, American University of the Middle East, Egaila, KuwaitThis study presents the results of an investigation into effectiveness of one-step and multi-step (h-step-ahead) forecasting methods in mitigating the Bullwhip Effect and improving supply chain performance within an order-up-to-level inventory control system. the Bullwhip Effect, a phenomenon in which small variations in consumer demand cause increasingly larger fluctuations upstream in the supply chain, presents significant challenges for inventory management and cost control. Traditional forecasting methods, such as Moving Average and Exponential Smoothing, have been extensively studied for their impact on supply chain performance. This study is among the first to introduce machine learning forecasting models, specifically Long Short-Term Memory and LightGBM, within this research domain, comparing their performance under various demand conditions, including autoregressive processes with and without seasonality, as well as the well-known M5 forecasting competition dataset. The results reveal that the multi-step-ahead forecasting capability of Long Short-Term Memory and LightGBM significantly outperforms one-step-ahead forecasting in reducing demand amplification, leading to improvements in key supply chain metrics such as order fulfillment rate, variance of inventory, and average end inventory across all autoregressive and M5 series. The findings demonstrate the superior accuracy and stability of machine-learning methods, particularly in scenarios with high demand autocorrelation, seasonality, and variability. These results provide new insights into the potential of advanced forecasting techniques to better manage supply chain variability and reduce the Bullwhip Effect, thereby offering valuable guidance for optimizing inventory control strategies.https://ieeexplore.ieee.org/document/10772207/Bullwhip effect (BWE)supply chain performancemachine learning forecastinglong short-term memory (LSTM)LightGBMmulti-step forecasting
spellingShingle Alper Saricioglu
Mujde Erol Genevois
Michele Cedolin
Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain Performance
IEEE Access
Bullwhip effect (BWE)
supply chain performance
machine learning forecasting
long short-term memory (LSTM)
LightGBM
multi-step forecasting
title Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain Performance
title_full Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain Performance
title_fullStr Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain Performance
title_full_unstemmed Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain Performance
title_short Analyzing One-Step and Multi-Step Forecasting to Mitigate the Bullwhip Effect and Improve Supply Chain Performance
title_sort analyzing one step and multi step forecasting to mitigate the bullwhip effect and improve supply chain performance
topic Bullwhip effect (BWE)
supply chain performance
machine learning forecasting
long short-term memory (LSTM)
LightGBM
multi-step forecasting
url https://ieeexplore.ieee.org/document/10772207/
work_keys_str_mv AT alpersaricioglu analyzingonestepandmultistepforecastingtomitigatethebullwhipeffectandimprovesupplychainperformance
AT mujdeerolgenevois analyzingonestepandmultistepforecastingtomitigatethebullwhipeffectandimprovesupplychainperformance
AT michelecedolin analyzingonestepandmultistepforecastingtomitigatethebullwhipeffectandimprovesupplychainperformance