Multi-product expedited ordering with demand forecast updates

Zhang, Bin; Duan, Deliang; Ma, Yurui

doi:10.1016/j.ijpe.2018.09.034

Cited by 12 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2017 Gaba et al [6] considering some heuristics to combine forecast intervals and compare their performance, obtaining satisfactory results. Other researches [7] studies the problem of multiple product purchases, demand forecast updates and orders. Classification criteria for forecasting methods are also provided [8].…”

Section: Related Workmentioning

confidence: 99%

A Comparison of Machine Learning and Classical Demand Forecasting Methods: A Case Study of Ecuadorian Textile Industry

Lorente-Leyva

Alemany

Peluffo-Ordóñez

et al. 2020

Machine Learning, Optimization, and Data Science

View full text Add to dashboard Cite

This document presents a comparison of demand forecasting methods, with the aim of improving demand forecasting and with it, the production planning system of Ecuadorian textile industry. These industries present problems in providing a reliable estimate of future demand due to recent changes in the Ecuadorian context. The impact on demand for textile products has been observed in variables such as sales prices and manufacturing costs, manufacturing gross domestic product and the unemployment rate. Being indicators that determine to a great extent, the quality and accuracy of the forecast, generating also, uncertainty scenarios. For this reason, the aim of this work is focused on the demand forecasting for textile products by comparing a set of classic methods such as ARIMA, STL Decomposition, Holt-Winters and machine learning, Artificial Neural Networks, Bayesian Networks, Random Forest, Support Vector Machine, taking into consideration all the above mentioned, as an essential input for the production planning and sales of the textile industries. And as a support, when developing strategies for demand management and medium-term decision making of this sector under study. Finally, the effectiveness of the methods is demonstrated by comparing them with different indicators that evaluate the forecast error, with the Multi-layer Neural Networks having the best results with the least error and the best performance.

show abstract

Section: Related Workmentioning

confidence: 99%

A Comparison of Machine Learning and Classical Demand Forecasting Methods: A Case Study of Ecuadorian Textile Industry

Lorente-Leyva

Alemany

Peluffo-Ordóñez

et al. 2020

Machine Learning, Optimization, and Data Science

View full text Add to dashboard Cite

show abstract

“…Genetic algorithm is a computational model that simulates the natural evolution of Darwin's biological evolution theory and the biological evolution process of genetic mechanism [6]. It is a method to search for optimal solutions by simulating natural evolutionary processes.In machine learning applications, the algorithm automatically selects the most appropriate model and parameters based on the input training data and tags, just like evolution.The steps of the algorithm are as follows.…”

Section: Genetic Algorithmmentioning

confidence: 99%

An Approach of Data Processing and Sales Prediction Model for E-commerce Platform

Chen¹,

Wen²,

Chen³

et al. 2019

IJCATR

View full text Add to dashboard Cite

For the e-commerce platform, obtaining sales status of the stores is important for formulating sale strategies, risk assessment plans and loan appraisal. The traditional way to obtain sales status is mainly based on the subjective judgment of relevant practitioners and the analysis of mathematical statistical models composed of historical data. These methods are inaccurate and too dependent on people's judgment. Therefore, using data mining and machine learning technology to predict the sales amount came into being. In this paper, we propose a method to process a great deal of data from China's famous e-commerce platform called Jingdong. This method can make the messy data become uniform data sets which are more suitable for machine learning. Based on the uniform data sets, two sales prediction models are used to predict the sales amount of the stores in Jingdong. In experiment, 9-month historical sales and behavior data of 10,000 stores in Jingdong platform are processed by the proposed method. Furthermore, two prediction models including GBDT(Gradient Boosting Decision Tree)+DNN(Deep neural network) and GA(genetic algorithm) are used to predict the sales amount of stores in following 3 months. To verify the accuracy of the prediction, we import WMAE(Weighted Mean Average Error)score. In experimental results, the best WMAE is 0.39, which means accuracy is 61%. It shows the method of data processing and prediction models are effective compare with other models. This indicates the proposed method and model can be used for sales prediction in e-commerce platform.

show abstract

“…The basic characteristic of demand is the driving force behind the existence of products in the commodity economy. Whether it is the traditional real economy or the new economic model based on "Internet +", the ultimate goal of all business operators is to maximize profits [13,14]. We believe that in a traditional economy, product price is the decisive factor affecting consumer demand and purchase patterns [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

A new demand function graph: Analysis of retailer-to-individual customer product supply strategies under a non-essential demand pattern

Zhuo,

Chen,

Yan

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

The core objective of a successful product supply strategy is to determine the mechanism through which consumers’ psychological effects influence customer demand. As stated in the theory of supply and demand, a higher level of dynamic equilibrium should be formed in which demand drives supply and supply creates demand. There is a lack of systematic research in the literature on the identification of consumer goods demand attributes and the formation of influencing factors in consumer goods supply chains. In this paper, we use the literature on demand functions and product pricing functions to establish three mathematical models to study the factors that influence retailers in designing and planning product supply strategies for different customers under nonessential demand patterns and to solve the profit maximization problem. The results of numerical examples validate the validity of the model. The research results can help retailers develop different supply strategies according to different types of customers and different demand patterns, thereby improving business performance. The theoretical contribution of this study is the construction of value ranges and a demand function diagram for identifying consumer product demand attributes.

show abstract

Multi-product expedited ordering with demand forecast updates

Cited by 12 publications

References 38 publications

A Comparison of Machine Learning and Classical Demand Forecasting Methods: A Case Study of Ecuadorian Textile Industry

A Comparison of Machine Learning and Classical Demand Forecasting Methods: A Case Study of Ecuadorian Textile Industry

An Approach of Data Processing and Sales Prediction Model for E-commerce Platform

A new demand function graph: Analysis of retailer-to-individual customer product supply strategies under a non-essential demand pattern

Contact Info

Product

Resources

About