scholarly journals Improving intermittent demand forecasting based on data structure

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
S. Fatemeh Faghidian ◽  
◽  
Mehdi Khashei ◽  
Mohammad Khalilzadeh ◽  
◽  
...  
Keyword(s):  
Hybrid Model ◽  
Prediction Models ◽  
Moving Average ◽  
Demand Forecasting ◽  
Spare Parts ◽  
Percentage Error ◽  
Complex Nature ◽  
Intermittent Demand ◽  
Classical Models ◽  
The Cost

Forecasting spare parts requirements is a challenging problem, because the normally intermittent demand has a complex nature in patterns and associated uncertainties, and classical forecasting approaches are incapable of modeling these complexities. The present study introduces a hybrid model that can impressively overcome the limitations of classical models while simultaneously using their unique advantages in dealing with the complexities in intermittent demand. The strategy of the proposed hybrid model is to use the three individual autoregressive moving average (ARMA), single exponential smoothing (SES), and multilayer perceptron (MLP) models simultaneously. Each of them has the potential of modeling a different structure and patterns of behavior among the data. The accuracy in forecasting ability is also increased by the suitable examination of these in the intermittent data. Croston’s method is the backbone of the suggested model. The proposed hybrid model is based on CV2 and ADI criteria, which improve its efficacy in examining inappropriate structures by reducing the cost of inappropriate modeling while increasing the prediction model accuracy. Using these results prevents the hybrid model from being confused or weakened in the modeling of all groups and reduces the risk of choosing the disproportionate model. The accuracy of prediction models was evaluated and compared using mean absolute percentage error (MAPE) by implementing an example, and promising results were achieved.

scholarly journals Intermittent demand forecasting for aircraft inventories: a study of Brazilian’s Boeing 737NG aircraft´s spare parts management

TRANSPORTES ◽  
2019 ◽  
Vol 27 (2) ◽  
pp. 102-116
Author(s):  
Jersone Tasso Moreira Silva ◽  
Luiz Henrique Santos ◽  
Alexandre Teixeira Dias ◽  
Hugo Ferreira Braga Tadeu
Keyword(s):  
Moving Average ◽  
Demand Forecasting ◽  
Exponential Smoothing ◽  
Spare Parts ◽  
Next Generation ◽  
Intermittent Demand ◽  
Spare Parts Management ◽  
Single Exponential ◽  
Airline Company

Este estudo tem como objetivo avaliar cinco métodos de previsão para demanda intermitente usando uma série histórica de consumo de peças sobressalentes da aeronave 737 Next Generation, fabricado pela Boeing, da maior frota aérea brasileira gerenciada pela VRG Airline Company S/A. Os métodos de Winter, Croston, Single Exponential Smoothing, Weight Moving Average e Método de Distribuição de Poisson foram testados em um histórico de 53 peças sobressalentes e cada uma delas possui um histórico de demanda de trinta e seis meses (janeiro de 2013 a dezembro de 2015). Os resultados mostraram que os métodos Weight Moving Average, Distribuição de Poisson e Croston apresentaram os melhores ajustes. Além disso, observou-se que a maior parte das demandas por peças sobressalentes apresentaram um padrão smooth ao contrário do resultado obtido pelo estudo de Ghobbar and Friend (2003) que apresentou um padrão lumpy. Por outro lado, tem-se que o Método de Winter apresentou-se como o de pior ajuste em ambos os estudos. Conclui-se que os métodos de Weight Moving Average e Distribuição de Poisson são os mais adequados para avaliar a demanda intermitente para o caso da VRG Airline Company S/A.

scholarly journals Planning Production Capacity Using Time Series Forecasting Method and Linier Programming

2018 ◽  
Vol 7 (2) ◽  
pp. 20
Author(s):  
M. Tirtana Siregar ◽  
S. Pandiangan ◽  
Dian Anwar
Keyword(s):  
Average Method ◽  
Moving Average ◽  
Demand Forecasting ◽  
Production Capacity ◽  
Mean Absolute Percentage Error ◽  
Programming Method ◽  
Percentage Error ◽  
Absolute Percentage Error ◽  
Forecasting Method ◽  
Planning Production

The objectives of this research is to determine the amount of production planning capacity sow talc products in the future utilizing previous data from january to december in year 2017. This researched considered three forecasting method, there are Weight Moving Average (WMA), Moving Average (MA), and Exponential Smoothing (ES). After calculating the methods, then measuring the error value using a control chart of 3 (three) of these methods. After find the best forecasting method, then do linear programming method to obtain the exact amount of production in further. Based on the data calculated, the method of Average Moving has a size of error value of Mean Absolute Percentage Error of 0.09 or 9%, Weight Moving Average has a size error of Mean Absolute Percentage Error of 0.09 or 9% and with Exponential Method Smoothing has an error value of Mean Absolute Percentage Error of 0.12 or 12%. Moving Average and Weight Moving Average have the same MAPE amount but Weight Moving Average has the smallest amount Mean Absolute Deviation compared to other method which is 262.497 kg. Based on the result, The Weight Moving Average method is the best method as reference for utilizing in demand forecasting next year, because it has the smallest error size and has a Tracking Signal  not exceed the maximum or minimum control limit is ≤ 4. Moreover, after obtained Weight Moving Average method is the best method, then is determine value of planning production capacity in next year using linier programming method. Based on the linier programming calculation, the maximum amount of production in next year by considering the forecasting of raw materials, production volume, material composition, and production time obtained in one (1) working day is 11,217,379 pcs / year, or 934,781 pcs / month of finished product. This paper recommends the company to evaluate the demand forecasting in order to achieve higher business growth.

scholarly journals Comparative Performance of Prediction Methods for Digital Wallet Transactions in the Pandemic Period

2020 ◽  
Vol 4 (4) ◽  
pp. 642-647
Author(s):  
Arwin Datumaya Wahyudi Sumari ◽  
Muhammad Bisri Musthafa ◽  
Ngatmari ◽  
Dimas Rossiawan Hendra Putra
Keyword(s):  
Prediction Models ◽  
Positive Impact ◽  
Moving Average ◽  
Percentage Error ◽  
Market Place ◽  
National Scale ◽  
Comparative Performance ◽  
Digital World ◽  
A Company ◽  
Digital Wallet

A pandemic situation such as Covid-19 which is still ongoing has given significant impacts to various sectors such as education, economy, tourism, and social which is in turn impacting the community at a national scale. On the other hand, the pandemic situation has also brought a positive impact on companies engaged in finance that utilizes information technology, namely digital wallets, a company that runs a market place in the digital world. In an effort to anticipate a dynamic market place, the company needs to predict the movement of transactions from time to time by building a model and performain the simulation to such model. Based on this problem, this paper presents simulations on the prediction models based on methods namely, naïve, Single Moving Average (SMA), Exponential Moving Average (EMA), combined SMA-naive methods, combined EMA-naive methods, as well as did the comparison of the best performance of every model by using Mean Absolute Percentage Error (MAPE) measurement. From the results of comparison, it is concluded that exponential moving average method delivers the best performance as prediction tool with MAPE of 23,4%.

scholarly journals Comparison of Fuzzy Time Series and ARIMA to Forecast Tourist Arrivals to Homestay in Pahang

2021 ◽  
Vol 6 (4) ◽  
pp. 80-89
Author(s):  
Maizatul Akhmar Jafridin ◽  
Nur Fatihah Fauzi ◽  
Rohana Alias ◽  
Huda Zuhrah Ab Halim ◽  
Nurizatul Syarfinas Ahmad Bakhtiar ◽  
...  
Keyword(s):  
Time Series ◽  
Moving Average ◽  
Demand Forecasting ◽  
Secondary Data ◽  
Fuzzy Time Series ◽  
Percentage Error ◽  
Strategic Decisions ◽  
Forecasting Performance ◽  
Future Events ◽  
Time Series Method

Predictions of future events must be incorporated into the decision-making process. For tourism demand, forecasting is very important to help directors and investors to make decisions in operational, tactical, and strategic decisions. This study focuses on forecasting performance between Fuzzy Time Series and ARIMA to forecast the tourist arrivals in homestays in Pahang. The main objective of this study is to compare and identify the best method between Fuzzy Time Series and Autoregressive Integrated Moving Average (ARIMA) in forecasting the arrival of tourists based on the secondary data of tourist arrivals to homestay in Pahang from January 2015 to December 2018. ARIMA models are flexible and widely used in time-series analysis and Fuzzy Time Series which do not need large samples and long past time series. These two methods have been compared by using the mean square error (MSE) and mean absolute percentage error (MAPE) as the forecast measures of accuracy. The results show that Fuzzy Time Series outperforms the ARIMA. The lowest value of MSE and MAPE was obtained from using the Fuzzy Time Series method at values 2192305.89 and 11.92256, respectively.

scholarly journals Forecasting residential natural gas consumption in Egypt

2020 ◽  
Vol 2 (4) ◽  
pp. 297-308
Author(s):  
Mohamed Ali Ismail ◽  
Eman Mahmoud Abd El-Metaal
Keyword(s):  
Natural Gas ◽  
Moving Average ◽  
Percentage Error ◽  
Seasonal Patterns ◽  
Content Type ◽  
Cost Of Energy ◽  
Proposed Model ◽  
Gas Consumption ◽  
Natural Gas Consumption ◽  
The Cost

Purpose This paper aims to obtain accurate forecasts of the hourly residential natural gas consumption, in Egypt, taken into consideration the volatile multiple seasonal nature of the gas series. This matter helps in both minimizing the cost of energy and maintaining the reliability of the Egyptian power system as well. Design/methodology/approach Double seasonal autoregressive integrated moving average-generalized autoregressive conditional heteroskedasticity model is used to obtain accurate forecasts of the hourly Egyptian gas consumption series. This model captures both daily and weekly seasonal patterns apparent in the series as well as the volatility of the series. Findings Using the mean absolute percentage error to check the forecasting accuracy of the model, it is proved that the produced outcomes are accurate. Therefore, the proposed model could be recommended for forecasting the Egyptian natural gas consumption. Originality/value The contribution of this research lies in the ingenuity of using time series models that accommodate both daily and weekly seasonal patterns, which have not been taken into consideration before, in addition to the series volatility to forecast hourly consumption of natural gas in Egypt.

scholarly journals Forecasting Electricity Consumption Using Time Series Model

2018 ◽  
Vol 7 (4.30) ◽  
pp. 218 ◽  
Author(s):  
Y.W. Lee ◽  
K.G. Tay ◽  
Y.Y. Choy
Keyword(s):  
Mean Square Error ◽  
Future Development ◽  
Linear Trend ◽  
Moving Average ◽  
Demand Forecasting ◽  
Electricity Consumption ◽  
Electricity Sector ◽  
Percentage Error ◽  
Mean Square ◽  
Monthly Electricity Consumption

Electricity demand forecasting is important for planning and facility expansion in the electricity sector.  Accurate forecasts can save operating and maintenance costs, increased the reliability of power supply and delivery system, and correct decisions for future development.  Universiti Tun Hussein Onn Malaysia (UTHM) which is a developing university in Malaysia has been growing since its formation in 1993.  Thus, it is important for UTHM to forecast the electricity consumption in future so that the future development can be determined.  Hence, UTHM electricity consumption was forecasted by using the simple moving average (SMA), weighted moving average (WMA), simple exponential smoothing (SES), Holt linear trend (HL), Holt-Winters (HW) and centered moving average (CMA).  The monthly electricity consumption from January 2011 to December 2017 was used to forecast January to December 2018 monthly electricity consumption.  HW gives the smallest mean absolute error (MAE) and mean absolute percentage error (MAPE), while CMA produces the lowest mean square error (MSE) and root mean square error (RMSE).  As there is a decreasing population of UTHM after the moving of four faculties to Pagoh and HW forecasted trend is decreasing whereas CMA is increasing, hence HW might forecast better in this problem.

scholarly journals Intermittent Demand Forecasting for Spare Parts: A Critical Review

Omega ◽  
2021 ◽  
pp. 102513
Author(s):  
Çerağ Pinçe ◽  
Laura Turrini ◽  
Joern Meissner
Keyword(s):  
Critical Review ◽  
Demand Forecasting ◽  
Spare Parts ◽  
Intermittent Demand

scholarly journals Forecasting spare parts demand using condition monitoring information

2019 ◽  
Vol 26 (1) ◽  
pp. 53-68
Author(s):  
Nzita Alain Lelo ◽  
P. Stephan Heyns ◽  
Johann Wannenburg
Keyword(s):  
Natural Frequency ◽  
Demand Forecasting ◽  
Fatigue Tests ◽  
Spare Parts ◽  
Just In Time ◽  
Base Excitation ◽  
Content Type ◽  
Forecasting Methods ◽  
Spare Parts Management ◽  
The Cost

Purpose The control of an inventory where spare parts demand is infrequent has always been difficult to manage because of the randomness of the demand, as well as the existence of a large proportion of zero values in the demand pattern. The purpose of this paper is to propose a just-in-time (JIT) spare parts availability approach by integrating condition monitoring (CM) with spare parts management by means of proportional hazards models (PHM) to eliminate some of the shortcomings of the spare parts demand forecasting methods. Design/methodology/approach In order to obtain the event data (lifetime) and CM data (first natural frequency) required to build the PHM for the spares demand forecasting, a series of fatigue tests were conducted on a group of turbomachinery blades that were systematically fatigued on an electrodynamic shaker in the laboratory, through base excitation. The process of data generation in the numerical as well as experimental approaches comprised introducing an initial crack in each of the blades and subjecting the blades to base excitation on the shaker and then propagating the crack. The blade fatigue life was estimated from monitoring the first natural frequency of each blade while the crack was propagating. The numerical investigation was performed using the MSC.MARC/2016 software package. Findings After building the PHM using the data obtained during the fatigue tests, a blending of the PHM with economic considerations allowed determining the optimal risk level, which minimizes the cost. The optimal risk point was then used to estimate the JIT spare parts demand and define a component replacement policy. The outcome from the PHM and economical approach allowed proposing development of an integrated forecasting methodology based not only on failure information, but also on condition information. Research limitations/implications The research is simplified by not considering all the elements usually forming part of the spare parts management study, such as lead time, stock holding, etc. This is done to focus the attention on component replacement, so that a just-in-time spare parts availability approach can be implemented. Another feature of the work relates to the decision making using PHM. The approach adopted here does not consider the use of the transition probability matrix as addressed by Jardine and Makis (2013). Instead, a simulation method is used to determine the optimal risk point which minimizes the cost. Originality/value This paper presents a way to address some existing shortcomings of traditional spare parts demand forecasting methods, by introducing the PHM as a tool to forecast spare parts demand, not considering the previous demand as is the case for most of the traditional spare parts forecasting methods, but the condition of the parts in operation. In this paper, the blade bending first mode natural frequency is used as the covariate in the PHM in a laboratory experiment. The choice of natural frequency as covariate is justified by its relationship with structural stiffness (and hence damage), as well as being a global parameter that could be measured anywhere on the blade without affecting the results.

scholarly journals Time Series Clustering of Electricity Demand for Industrial Areas on Smart Grid

Energies ◽  
2020 ◽  
Vol 13 (9) ◽  
pp. 2377
Author(s):  
Heung-gu Son ◽  
Yunsun Kim ◽  
Sahm Kim
Keyword(s):  
Time Series ◽  
Smart Grid ◽  
Moving Average ◽  
Demand Forecasting ◽  
Prediction Method ◽  
Electricity Demand ◽  
Percentage Error ◽  
Autoregressive Moving Average ◽  
Clustering Methods ◽  
Time Series Clustering

This study forecasts electricity demand in a smart grid environment. We present a prediction method that uses a combination of forecasting values based on time-series clustering. The clustering of normalized periodogram-based distances and autocorrelation-based distances are proposed as the time-series clustering methods. Trigonometrical transformation, Box–Cox transformation, autoregressive moving average (ARMA) errors, trend and seasonal components (TBATS), double seasonal Holt–Winters (DSHW), fractional autoregressive integrated moving average (FARIMA), ARIMA with regression (Reg-ARIMA), and neural network nonlinear autoregressive (NN-AR) are used for demand forecasting based on clustering. The results show that the time-series clustering method performs better than the method using the total amount of electricity demand in terms of the mean absolute percentage error (MAPE).

Sign in / Sign up

Export Citation Format

Share Document