Application of machine learning techniques for supply chain demand forecasting

@article{Carbonneau2008ApplicationOM,
  title={Application of machine learning techniques for supply chain demand forecasting},
  author={R{\'e}al Andr{\'e} Carbonneau and Kevin Laframboise and Rustam M. Vahidov},
  journal={Eur. J. Oper. Res.},
  year={2008},
  volume={184},
  pages={1140-1154}
}
Machine learning demand forecasting and supply chain performance
  • J. Feizabadi
  • Business
    International Journal of Logistics Research and Applications
  • 2020
TLDR
In many supply chains, firms staged in upstream of the chain suffer from variance amplification emanating from demand information distortion in a multi-stage supply chain and, consequently, their performance and profits are adversely affected.
A Neural Network Sustainable Hybrid Model to Reliable Forecast the Supply-Chain Demand
TLDR
A sustainable hybrid model using a combination of several artificial neural networks such as Principal Component Analysis, Self-Organization Map, and Multi-Layer Perceptron network, to provide a solution to overcome the challenge of demand forecasting by giving a reliable forecast for demand, with acceptable accuracy.
Machine learning for demand forecasting in the physical internet: a case study of agricultural products in Thailand
TLDR
The results prove the better forecasting efficiency of the LSTM method with continuous fluctuating demand, whereas the others offer greater performance with less varied demand and the performance of hybrid metaheuristics is higher than with trial-and-error.
Forecasting Demand in Supply Chain Using Machine Learning Algorithms
  • N. Ampazis
  • Business, Computer Science
    Int. J. Artif. Life Res.
  • 2015
TLDR
The approach presented in this paper combines the integration of data from various sources of information and the power of advanced machine learning algorithms for lowering the uncertainty barrier in forecasting supply chain demand.
Demand Forecasting using Artificial Neuronal Networks and Time Series: Application to a French Furniture Manufacturer Case Study
TLDR
Using cross-validation, early stopping, robust learning algorithm, optimal structure determination and taking the mean of the month turns out to be a good way to get enough close to the current forecasting system.
FORECASTING OF DEMAND USING ARTIFICIAL NEURAL NETWORK FOR SUPPLY CHAIN MANAGEMENT
TLDR
It was observed that as forecasting period becomes smaller, the ANN approach provides more accuracy in forecast and is also imposed to better prediction of time series in future.
DEMAND FORECASTING USING NEURAL NETWORK FOR SUPPLY CHAIN MANAGEMENT
TLDR
It was observed that as forecasting period becomes smaller, the ANN approach provides more accuracy in forecast and is also imposed to better prediction of time series in future.
A Computational Intelligence Approach to Supply Chain Demand Forecasting
TLDR
The effectiveness of the proposed approach was evaluated using public data from the Netflix movie rental online DVD store in order to predict the demand for movie rentals during the critical, for sales, Christmas holiday season.
Machine Learning Applications in Supply Chain Management: A Deep Learning Model Using an Optimized LSTM Network for Demand Forecasting
TLDR
The proposed deep learning method based on long-term memory multilayer networks (LSTM) for demand forecasting has shown strength in capturing the existing nonlinear features in time series data compared to some known time series forecasting methods derived from statistical and machine learning approaches.
Revisiting the Effects of Forecasting Method Selection and Information Sharing Under Volatile Demand in SCM Applications
TLDR
It is shown that advanced forecasting methods such as generalized autoregressive conditional heteroscedasticity and properly configured neural network models significantly reduce costs relative to the conventional forecasting methods under most scenarios examined, but misspecified models often result in poor system performance.
...
...

References

SHOWING 1-10 OF 42 REFERENCES
The Bullwhip Effect In Supply Chain
In a supply chain the variability of the orders received by the supplier can be greater than the demand variability. This phenomenon is named bullwhip effect. Some researchers are quantified the
The Impact of Forecast Errors on Early Order Commitment in a Supply Chain
TLDR
It is found that practicing early order commitment can generate significant savings in the supply chain, but the benefits are only valid within a range of order commitment periods.
Measuring and avoiding the bullwhip effect: A control theoretic approach
Interorganizational Collaborative Forecasting and Replenishment Systems and Supply Chain Implications
Collaborative Forecasting and Replenishment (CFAR) is a new interorganizational system that enables retailers and manufacturers to forecast demand and schedule production jointly. The capabilities of
Improving supply-chain performance by sharing advance demand information
Noisy Time Series Prediction using Symbolic Representation and Recurrent Neural Network Grammatical Inference
TLDR
A new intelligent signal processing method is introduced which addresses the difficulties of financial forecasting by using conversion into a symbolic representation with a self-organizing map, and grammatical inference with recurrent neural networks.
Neural Networks in Economics: Background, Applications and New Developments
TLDR
The ideas from Statistical Learning Theory, introduced in Section 2, lead the way to the so called Support Vector learning, which will be described in Section 5 for the task of classification.
e-Business and Supply Chain Management
TLDR
This paper highlights strategic and tactical issues for analyzing supply chains in an e-business setting based on papers published in this special issue and describes future research opportunities in this emerging interdisciplinary area.
...
...