Forecasting Aviation Spare Parts Demand Using Croston Based Methods and Artificial Neural Networks (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.
Automobile spare-parts forecasting: A comparative study of time series methods
International Journal of Automotive and Mechanical Engineering, 2017
In Mexico, the automotive industry is considered to be strategic in the industrial and economic development of the country because it generates production, employment and foreign exchange. Good demand forecasts are needed for better manufacturing management. The time series modelling tools applied to the monthly demand forecasting of automobile spare parts in Mexico are assessed, for the case of a transnational enterprise, considering affordability. The classic methods of moving averages, final value and exponential smoothing, the prestigious autoregressive integrated models of moving averages (ARIMA), the rarely implemented artificial neural networks (ANNs) and the very little explored ARIMA-ANNs hybrid models are compared. A good performance of the models involving ANNs is observed, but they were not as steady as the ARIMA models in the post-sample periods. The mean absolute percentage error (MAPE) was reduced from an original 57% to 32.65%. The obtained results could help demonstrate the importance of improving industrial forecasting methodologies for better planning.
Electrical Spare Parts Demand Forecasting
Elektronika ir Elektrotechnika, 2014
In this paper is presented a research of electrical spare parts demand forecasting through application of conventional (moving average, exponential smoothing and naive theory), more sophisticated forecasting techniques (support vector regression, feed-forward neural networks) and adaptive model selection methodologies. Electrical spare parts demand forecasting is a fundamental task that should be performed in order to improve SCM (supply chain management). If it would be possible to know what the demand for electrical parts will be in the future, the logistics of the companies that manufacture electrical parts or retailers could be managed more accurately: selection of appropriate warehouse safety limits for each part and ability to plan the resources more precisely. Customer sales and marketing departments always perform formal forecasts, this is usually done through application of conventional methods in order to prepare future plans. Experimental results reveal that application of SVR technique guarantees the best and precise results of forecasting of weekly and daily demand of electrical parts. Furthermore, application of adaptive methodology in order to select adaptive model allowed substantially to increase forecasting accuracy.
A Hybrid Neural Network And Traditional Approach For Forecasting Lumpy Demand
2008
Accurate demand forecasting is one of the most key issues in inventory management of spare parts. The problem of modeling future consumption becomes especially difficult for lumpy patterns, which characterized by intervals in which there is no demand and, periods with actual demand occurrences with large variation in demand levels. However, many of the forecasting methods may perform poorly when demand for an item is lumpy. In this study based on the characteristic of lumpy demand patterns of spare parts a hybrid forecasting approach has been developed, which use a multi-layered perceptron neural network and a traditional recursive method for forecasting future demands. In the described approach the multi-layered perceptron are adapted to forecast occurrences of non-zero demands, and then a conventional recursive method is used to estimate the quantity of non-zero demands. In order to evaluate the performance of the proposed approach, their forecasts were compared to those obtained ...
2020
Sporadic demand presents a particular challenge to traditional time forecasting methods. In the past 50 years, there has been developments, such as, the Croston Model [3], which has improved forecast performance. With the rise of Machine Learning (ML) there is abundant research in the field of applying ML algorithms to predict sporadic demand [8][12][9]. However, most existing research has analyzed this problem from the demand side [17]. In this paper, we tackle this predictive analytics challenge from the supply side. We perform a comparative analysis utilizing a spare parts demand dataset from an Original Equipment Manufacturer (OEM). Since traditional measurements of forecast are unsuitable for sporadic demand data because of its sparse nature, we propose a novel method to forecast performance measurement which incorporates the trade-off of economic gains and obsolescence risks incurred.
Emerging Markets : Business and Management Studies Journal
The global economic crisis has reached the world today, forcing many customers to become more cost aware in their search for better quality and service, and forcing corporate organizations to discover more effective and efficient ways to compete among them. The main objective of this research is to choose the best forecasting method to predict the demandfor spare parts at PT. XYZ highly fluctuating, and to avoid or minimize stockouts. The demand for high-priced spare partsand capital goods is considered discontinuous if it is random and contributes a large part of the inventory value. Fluctuating demand for goods will be difficult to predict, and inaccurate estimates can cause huge losses for the company due to obsolescence of spare parts or unfulfilled demand for spare parts. Running a successful company operation today requires organizational strength to supply the needs of its customers. This study discusses the appropriate demand forecasting method for the fluctuation demand for...
Proper forecasting is imperative in making production, marketing, and inventory decisions in many fields, especially in the automotive industry. Different quantitative analysis techniques were applied in this study to predict demands in automotive spare parts for inventory management. The study is applied on a service station of a transportation company where, due to the current financial constraints brought about by inflation, the company changed its ordering of spare parts from every two months to a monthly basis. This paper used twelve months of historical data to predict future values of the spare parts. Naïve, Moving Averages, Weighted Moving Averages, and Exponential Smoothing forecasting techniques were applied to predict the future values of spare parts. The results of each technique were compared which demonstrated that the Exponential Smoothing and Weighted Moving Averages can be used to deliver the most reliable predictions to help inventory optimization and strategic planning significantly. These two methods brought substantial improvements in forecast accuracy when applied to the studied case. They can be considered to be the key to operational efficiency and satisfying dynamic demand in the aftermarket of automotive spare parts.
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.
Forecasting of Optimum Raw Material Inventory Level using Artificial Neural Network
This paper develops an artificial neural network (ANN) model to forecast the optimum level of raw materials inventory as a function of product demand, manufacturing lead-time, supplier reliability, material holding cost, and material cost. The model selects a feed-forward back-propagation ANN with twelve hidden neurons as the optimum network. We test the model with pharmaceutical company data. The results show that the model can be useful to forecast raw material inventory level in response to different parameters. We also compare the model with fuzzy inference system (FIS) and simple economic order quantity (EOQ). It can be seen that ANN model outperforms others. Overall, the model can be applied for forecasting of raw materials inventory for any manufacturing enterprise in a competitive business environment.
Artificial Neural Networks in the Demand Forecasting of a Metal-Mechanical Industry
Journal of Engineering and Applied Sciences
This research presents an application of artificial neural networks in demand forecasting by using MATLAB Software. Keeping in mind that in any planning process forecasts play a fundamental role, being one of the bases for; planning, organizing and controlling production. It gives priority to the most critical nodes and their key activities, so that, the decisions made about them will generate the greatest possible positive impact. The methodology applied demonstrates the quality of the solutions found which are compared with traditional statistical methods to demonstrate the value of the solution proposed. When the results show that the minimum quadratic error is reached with the application of artificial neural networks, a better performance is obtained. Therefore, a suitable horizon is established for the planification and decision making in the metal-mechanical industry for the use of artificial intelligence in the production processes.