A Hybrid Neural Network And Traditional Approach For Forecasting Lumpy Demand (original) (raw)
Related papers
Spare Part Demand Forecasting in Automotive Industry Using Artificial Neural Network
2021
The development of business in Indonesia today has developed rapidly, resulting the competition in the business become very competitive. One of the business line that currently developing rapidly is automotive industry. Each of automotive company trying to be able to win the hearts of customer with all the best offers and services, so they remain loyal to the product of company. A good management system needs to respond for local, regional, and national markets demand quickly. If business cannot fulfill the market demand quickly, the customer may change their willingness for purchase the products or services that sold by the company. In this paper, an Artificial Neural Network (ANN) was designed to help automotive distributor company predict Spare Part demand in each of Province in Indonesia. ANN was chosen since the method can model the situations, where highly nonlinear relationships among the variables can be captured.
Lumpy demand forecasting using neural networks
The current study applies neural network (NN) modeling in forecasting lumpy demand. It is, to the best of our knowledge, the first such study. Our study compares the performance of NN forecasts to those using three traditional timeseries methods (single exponential smoothing, Croston's method, and the Syntetos–Boylan approximation). We find NN models to generally perform better than the traditional methods, using three different performance measures. We also independently validate earlier findings that the Syntetos–Boylan approximation performs better than the Croston's and single exponential smoothing methods in lumpy demand forecasting. r
In the paper the problem of demand forecasting with the usage of artificial neural networks (ANN) is presented. The literature review was prepared and analyzed. The related numerical example was prepared based on the data from an distribution enterprise. The results from using the proposed neural model were compared with the results of using exponential smoothing methods and seasonal indices forecasting methods. An impact of an established demand forecast on inventory level has been discussed.
A Neural Approach to Product Demand Forecasting
International Journal of Industrial and Systems Engieering, 2013
This paper develops an artificial neural network (ANN) model to forecast the optimum demand as a function of time of the year, festival period, promotional programmes, holidays, number of advertisements, cost of advertisements, number of workers and availability. The model selects a feed-forward back-propagation ANN with 13 hidden neurons in one hidden layer as the optimum network. The model is validated with a furniture product data of a renowned furniture company. The model has also been compared with a statistical linear model named Brown's double smoothing model which is normally used by furniture companies. It is observed that ANN model performs much better than the linear model. Overall, the proposed model can be applied for forecasting optimum demand level of furniture products in any furniture company within a competitive business environment.
DEMAND FORECASTING USING NEURAL NETWORK FOR SUPPLY CHAIN MANAGEMENT
The demand forecasting technique which is modeled by artificial intelligence approaches using artificial neural networks. The consumer product causers the difficulty in forecasting the future demand and the accuracy of the forecast In performance of the artificial neural network an advantage in a constantly changing business environment and demand forecasting an organization in order to make right decisions regarding manufacturing and inventory management. The learning algorithm of the prediction is also imposed to better prediction of time series in future. The prediction performance of recurrent neural networks a simulated time series data and a practical sales data have been used. This is because of influence of several factors on demand function in retail trading system. It was also observed that as forecasting period becomes smaller, the ANN approach provides more accuracy in forecast.
Improved supply chain management based on hybrid demand forecasts
Applied Soft Computing, 2007
Demand forecasts play a crucial role for supply chain management. The future demand for a certain product is the basis for the respective replenishment systems. Several forecasting techniques have been developed, each one with its particular advantages and disadvantages compared to other approaches. This motivates the development of hybrid systems combining different techniques and their respective strengths. In this paper, we present a hybrid intelligent system combining Autoregressive Integrated Moving Average (ARIMA) models and neural networks for demand forecasting. We show improvements in forecasting accuracy and propose a replenishment system for a Chilean supermarket, which leads simultaneously to fewer sales failures and lower inventory levels than the previous solution. # 2005 Published by Elsevier B.V.
An Improved Neural Approaches for Forecasting Demand in Supply Chain Management
International Journal of Computer Applications
Demand forecasting plays a pivotal role for supply chain management. It allows predicting and meeting future demands of the product and expectations of customers. Several forecasting techniques have been developed, each one has its particular benefits and limitations compared to other approaches. This motivates the development of artificial neural networks (ANNs) to make intelligent decisions while taking advantage of today's processing power. Well, this paper deals with an improved algorithm for feedforward neural networks. Initially, the neural modelling process will be discussed. The approach adopted of neural modeling will be presented in a second time; this method is based on mononetwork neural modeling and multi-network neural modeling. The results of simulation obtained will be illustrated by a simulated time series data.
Forecasting Aviation Spare Parts Demand Using Croston Based Methods and Artificial Neural Networks
Accurate forecasting of spare parts demand not only minimizes inventory cost it also reduces the risk of stock-out. Though we have many techniques to forecast demand, majority of them cannot be applied to spare parts demand forecasting. Spare parts demand data usually have many zeros which makes conventional forecasting methods less effective. In this study we have used latest parametric time series methods and artificial neural networks to forecast spare parts demand of an aviation company. We have shown that with careful selection of the algorithm and their parameters the artificial neural network models give accurate forecasts for spare parts demand. Applying the proposed forecasting methods in aviation maintenance and repair companies will reduce inventory cots and eliminate risks of keeping planes on the ground. JEL Classification Codes: C45, C53.
Forecasting of Demand Using Artificial Neural Network for Supply Chain Management
2015
The demand forecasting technique which is modeled by artificial intelligence approaches using artificial neural networks. The consumer product causers the difficulty in forecasting the future demand and the accuracy of the forecast In performance of the artificial neural network an advantage in a constantly changing business environment and demand forecasting an organization in order to make right decisions regarding manufacturing and inventory management. The learning algorithm of the prediction is also imposed to better prediction of time series in future. The prediction performance of recurrent neural networks a simulated time series data and a practical sales data have been used. This is because of influence of several factors on demand function in retail trading system. It was also observed that as forecasting period becomes smaller, the ANN approach provides more accuracy in forecast.
IFIP advances in information and communication technology, 2018
As the primary prerequisite of capacity planning, inventory control and order management, demand forecast is a critical issue in semiconductor supply chain. A great quantity of stock keeping units (SKUs) with intermittent demand patterns and distinctive lead-times need specific prediction respectively. It is difficult for companies in semiconductor supply chain to manage intricate inventory systems with the changeable nature of intermittent (lumpy) demand. This study aims to propose an integrated forecasting approach with recurrent neural network and parametric method for intermittent demand problems to support flexible decisions in inventory management, as a critical role in intelligent supply chain. An empirical study was conducted with product time series in a semiconductor company in Taiwan to validate the practicality of proposed model. The results suggest that the proposed hybrid model can improve forecast accuracy in demand management of semiconductor supply chain.