{"title":"用人工神经网络(ANN)方法进行饮用水产品需求预测以减少需求估算与实现之间的差距","authors":"R. Syafitri, A. Ridwan, Nia Novitasari","doi":"10.1145/3429789.3429844","DOIUrl":null,"url":null,"abstract":"Supply Chain has components such as vendors, manufacturers, factories, warehouses retailers, customers, etc. Every relationship between components must have good information in order to create informed business decisions. Sales forecast are part of a decline in supply chain function and are a way to predict future product sales. The large gap between demand forecasting and actual demand proves that the forecasting method used in forecasting is not quite right so it can cause high error rates. In this study, the calculation of demand forecasting using the Artificial Neural Network (ANN) method was chosen as a good method because ANN learning method that works through an iterative process using training data comparing the predicted value of the network each sample of data and the weight of the network relation in each process is modified to minimize the value of Mean Squared Error (MSE). With the right parameters and good training in the data, the error number at the ANN calculation output using MATLAB will produce demand forecasting numbers that are getting closer to the actual demand numbers. The application of the ANN method to demand forecasting can make improvements to the error value performance using the MSE, MAD equation. and MAPE. The decline in MSE in 2018 from 1,894,299,389 to 26,612,567, in 2019 from 1,035,177,794 to 16,889,433, and in 2020 from 426,876,921 to 2,647,350. The decline in MAD in 2018 from 42,089 to 3,324, in 2019 from 26,924 to 2,888, and in 2020 from 20,661 to 1,627. MAPE reduction in 2018 from 23% to 2%, 2019 from 15% to 2%, and in 2020 from 11% to 1%.","PeriodicalId":416230,"journal":{"name":"Proceedings of the 2021 International Conference on Engineering and Information Technology for Sustainable Industry","volume":"67 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Demand Forecasting for Drinking Water Products to Reduce Gap Between Estimation and Realization of Demand Using Artificial Neural Network (ANN) Methods in PT. XYZ\",\"authors\":\"R. Syafitri, A. Ridwan, Nia Novitasari\",\"doi\":\"10.1145/3429789.3429844\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Supply Chain has components such as vendors, manufacturers, factories, warehouses retailers, customers, etc. Every relationship between components must have good information in order to create informed business decisions. Sales forecast are part of a decline in supply chain function and are a way to predict future product sales. The large gap between demand forecasting and actual demand proves that the forecasting method used in forecasting is not quite right so it can cause high error rates. In this study, the calculation of demand forecasting using the Artificial Neural Network (ANN) method was chosen as a good method because ANN learning method that works through an iterative process using training data comparing the predicted value of the network each sample of data and the weight of the network relation in each process is modified to minimize the value of Mean Squared Error (MSE). With the right parameters and good training in the data, the error number at the ANN calculation output using MATLAB will produce demand forecasting numbers that are getting closer to the actual demand numbers. The application of the ANN method to demand forecasting can make improvements to the error value performance using the MSE, MAD equation. and MAPE. The decline in MSE in 2018 from 1,894,299,389 to 26,612,567, in 2019 from 1,035,177,794 to 16,889,433, and in 2020 from 426,876,921 to 2,647,350. The decline in MAD in 2018 from 42,089 to 3,324, in 2019 from 26,924 to 2,888, and in 2020 from 20,661 to 1,627. MAPE reduction in 2018 from 23% to 2%, 2019 from 15% to 2%, and in 2020 from 11% to 1%.\",\"PeriodicalId\":416230,\"journal\":{\"name\":\"Proceedings of the 2021 International Conference on Engineering and Information Technology for Sustainable Industry\",\"volume\":\"67 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-09-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2021 International Conference on Engineering and Information Technology for Sustainable Industry\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3429789.3429844\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2021 International Conference on Engineering and Information Technology for Sustainable Industry","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3429789.3429844","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Demand Forecasting for Drinking Water Products to Reduce Gap Between Estimation and Realization of Demand Using Artificial Neural Network (ANN) Methods in PT. XYZ
Supply Chain has components such as vendors, manufacturers, factories, warehouses retailers, customers, etc. Every relationship between components must have good information in order to create informed business decisions. Sales forecast are part of a decline in supply chain function and are a way to predict future product sales. The large gap between demand forecasting and actual demand proves that the forecasting method used in forecasting is not quite right so it can cause high error rates. In this study, the calculation of demand forecasting using the Artificial Neural Network (ANN) method was chosen as a good method because ANN learning method that works through an iterative process using training data comparing the predicted value of the network each sample of data and the weight of the network relation in each process is modified to minimize the value of Mean Squared Error (MSE). With the right parameters and good training in the data, the error number at the ANN calculation output using MATLAB will produce demand forecasting numbers that are getting closer to the actual demand numbers. The application of the ANN method to demand forecasting can make improvements to the error value performance using the MSE, MAD equation. and MAPE. The decline in MSE in 2018 from 1,894,299,389 to 26,612,567, in 2019 from 1,035,177,794 to 16,889,433, and in 2020 from 426,876,921 to 2,647,350. The decline in MAD in 2018 from 42,089 to 3,324, in 2019 from 26,924 to 2,888, and in 2020 from 20,661 to 1,627. MAPE reduction in 2018 from 23% to 2%, 2019 from 15% to 2%, and in 2020 from 11% to 1%.