Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments

Priore, Paolo; Ponte, Borja; Rosillo, Rafael; García, David de la Fuente

doi:10.1080/00207543.2018.1552369

Cited by 119 publications

(65 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 3. This is in line with Priore et al (2019) who, however, pursue a completely different online approach, cf. Sect.…”

Section: Discussionsupporting

confidence: 83%

“…Table 1 compares the studies mentioned above by contrasting their methods, objectives, and proposed order policies. With the exception of the policy proposed by Priore et al (2019), all order policies in Table 1 share an important characteristic: they are determined once only at the beginning of the planning horizon. In contrast, all available information at each echelon and especially in each period should be considered in the determination of the order policies to improve their performance by adjusting to the dynamics of the supply chain.…”

Section: Artificial Intelligence In Supply Chain Inventory Managementmentioning

confidence: 99%

“…Keshari et al (2018) therefore emphasise the need for such models. In a recent study, Priore et al (2019) apply inductive learning (based on a C4.5 classification algorithm) to determine an online as well as a static offline (one-shot) order policy. Moreover, they compare both policies and show the superiority of the online version.…”

Section: Artificial Intelligence In Supply Chain Inventory Managementmentioning

confidence: 99%

See 2 more Smart Citations

Artificial intelligence-based inventory management: a Monte Carlo tree search approach

Preil

Krapp

2021

Ann Oper Res

View full text Add to dashboard Cite

The coordination of order policies constitutes a great challenge in supply chain inventory management as various stochastic factors increase its complexity. Therefore, analytical approaches to determine a policy that minimises overall inventory costs are only suitable to a limited extent. In contrast, we adopt a heuristic approach, from the domain of artificial intelligence (AI), namely, Monte Carlo tree search (MCTS). To the best of our knowledge, MCTS has neither been applied to supply chain inventory management before nor is it yet widely disseminated in other branches of operations research. We develop an offline model as well as an online model which bases decisions on real-time data. For demonstration purposes, we consider a supply chain structure similar to the classical beer game with four actors and both stochastic demand and lead times. We demonstrate that both the offline and the online MCTS models perform better than other previously adopted AI-based approaches. Furthermore, we provide evidence that a dynamic order policy determined by MCTS eliminates the bullwhip effect.

show abstract

“…Table 3. This is in line with Priore et al (2019) who, however, pursue a completely different online approach, cf. Sect.…”

Section: Discussionsupporting

confidence: 83%

Section: Artificial Intelligence In Supply Chain Inventory Managementmentioning

confidence: 99%

Section: Artificial Intelligence In Supply Chain Inventory Managementmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence-based inventory management: a Monte Carlo tree search approach

Preil

Krapp

2021

Ann Oper Res

View full text Add to dashboard Cite

show abstract

“…Retailer, irrespective of online and offline retails, requires demand forecasts to support sales management (Thomassey 2010), capacity management (Aviv 2007;Doganis, Aggelogiannaki, and Sarimveis 2008), assortment planning (Dzyabura and Jagabathula 2018), order picking (Gils et al 2017) and for several other important decisions. The demand forecasts also have significant impact on inventory ordering policies in production and retail (Doganis, Aggelogiannaki, and Sarimveis 2008), and several models are presented in the literature which highlight the importance of demand forecast for the inventory management (Erlebacher 2000;Priore et al 2019). Moreover, demand forecasts also helps in planning the distribution, routing and logistics management in retail (Sillanpää and Liesiö 2018;Winkelhaus and Grosse 2020;Liu et al 2020).…”

Section: The Forecasting In Retailmentioning

confidence: 99%

Deep learning with long short-term memory networks and random forests for demand forecasting in multi-channel retail

Punia

Νικολόπουλος

Singh

et al. 2020

International Journal of Production Research

111

View full text Add to dashboard Cite

This paper proposes a novel forecasting method that combines the deep learning method -long shortterm memory (LSTM) networks and random forest (RF). The proposed method can model complex relationships of both temporal and regression type which gives it an edge in accuracy over other forecasting methods. We evaluated the new method on a real-world multivariate dataset from a multichannel retailer. We benchmark the forecasting performance of the new proposition against neural networks, multiple regression, ARIMAX, LSTM networks, and RF. We employed forecasting performance metrics to measure bias, accuracy, and variance, and the empirical evidence suggests that the new proposition is (statistically) significantly better. Furthermore, our method ranks the explanatory variables in terms of their relative importance. The empirical evaluations are replicated for longer forecasting horizons, and online and offline channels and the same conclusions hold; thus, advocating for the robustness of our forecasting proposition as well as the suitability in multi-channel retail demand forecasting.

show abstract

“…The ideal situation is to achieve and sustain the best balance between the supply and demand throughout the supply chain at minimum cost. However, in most situations, the required balance is missing and hard to achieve due to the unpredictability of the supply chain response under various operational conditions [1,2]. Supply chains face a common problem, the so-called the demand information distortion, in which the demand variability is amplified as demand information moves upstream in supply chain.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Variance Amplification and Service Level in a Supply Chain with Correlated Demand

et al. 2020

View full text Add to dashboard Cite

The bullwhip effect reflects the variance amplification of demand as they are moving upstream in a supply chain, and leading to the distortion of demand information that hinders supply chain performance sustainability. Extensive research has been undertaken to model, measure, and analyze the bullwhip effect while assuming stationary independent and identically distributed (i.i.d) demand, employing the classical order-up-to (OUT) policy and allowing return orders. On the contrary, correlated demand where a period’s demand is related to previous periods’ demands is evident in several real-life situations, such as demand patterns that exhibit trends or seasonality. This paper assumes correlated demand and aims to investigate the order variance ratio (OVR), net stock amplification ratio (NSA), and average fill rate/service level (AFR). Moreover, the impact of correlated demand on the supply chain performance under various operational parameters, such as lead-time, forecasting parameter, and ordering policy parameters, is analyzed. A simulation modeling approach is adopted to analyze the response of a single-echelon supply chain model that restricts return orders and faces a first order autoregressive demand process AR(1). A generalized order-up-to policy that allows order smoothing through the proper tuning of its smoothing parameters is applied. The characterization results confirm that the correlated demand affects the three performance measures and interacts with the operating conditions. The results also indicate that the generalized OUT inventory policy should be adopted with the correlated demand, as its smoothing parameters can be adapted to utilize the demand characteristics such that OVR and NSA can be reduced without affecting the service level (AFR), implying sustainable supply chain operations. Furthermore, the results of a factorial design have confirmed that the ordering policy parameters and their interactions have the largest impact on the three performance measures. Based on the above characterization, the paper provides management with means to sustain good performance of a supply chain whenever a correlated demand pattern is realized through selecting the control parameters that decrease the bullwhip effect.

show abstract

Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments

Abstract: The Open University's repository of research publications and other research outputs Applying machine learning to the dynamic selection of replenishment policies in fast-changing supply chain environments

Cited by 119 publications

References 58 publications

Artificial intelligence-based inventory management: a Monte Carlo tree search approach

Artificial intelligence-based inventory management: a Monte Carlo tree search approach

Deep learning with long short-term memory networks and random forests for demand forecasting in multi-channel retail

Analysis of Variance Amplification and Service Level in a Supply Chain with Correlated Demand

Contact Info

Product

Resources

About