Peramalan Penjualan Kendaraan Mobil Segmen B2B dengan Metode Regresi Linear Berganda, Jaringan Saraf Tiruan dan Jaringan Saraf Tiruan – Algoritma Genetika
Muhammad Agung Nugraha, F. Farizal, Djoko Sihono Gabriel
{"title":"Peramalan Penjualan Kendaraan Mobil Segmen B2B dengan Metode Regresi Linear Berganda, Jaringan Saraf Tiruan dan Jaringan Saraf Tiruan – Algoritma Genetika","authors":"Muhammad Agung Nugraha, F. Farizal, Djoko Sihono Gabriel","doi":"10.29303/emj.v3i2.80","DOIUrl":null,"url":null,"abstract":"This study aims to create an effective forecasting model in predicting sales of car products in the B2B segment (Business to Business) to obtain estimates of product sales in the future. This research uses multiple linear regression and artificial neural networks that are optimized by genetic algorithms. Forecasting factors for car sales are generally issued by total national car sales, the Consumer Price Index, the Consumer Confidence Index, the Inflation Rate, Gross Domestic Product (GDP), and Fuel Oil Price. The author has also gotten the factors that play a role in the sale of B2B segment by diverting the survey to 106 DMU (Decision Making Unit) who decide to purchase cars in their company. Then we evaluate the results of the questionnaire in training data and simulations on the Artificial Neural Network. Optimized Artificial Neural Networks with Genetic Algorithms can improve B2B segment car sales' accuracy when comparing error values in the ordinary Artificial Neural Network and Multiple Linear Regression.","PeriodicalId":281429,"journal":{"name":"EIGEN MATHEMATICS JOURNAL","volume":"126 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EIGEN MATHEMATICS JOURNAL","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.29303/emj.v3i2.80","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
This study aims to create an effective forecasting model in predicting sales of car products in the B2B segment (Business to Business) to obtain estimates of product sales in the future. This research uses multiple linear regression and artificial neural networks that are optimized by genetic algorithms. Forecasting factors for car sales are generally issued by total national car sales, the Consumer Price Index, the Consumer Confidence Index, the Inflation Rate, Gross Domestic Product (GDP), and Fuel Oil Price. The author has also gotten the factors that play a role in the sale of B2B segment by diverting the survey to 106 DMU (Decision Making Unit) who decide to purchase cars in their company. Then we evaluate the results of the questionnaire in training data and simulations on the Artificial Neural Network. Optimized Artificial Neural Networks with Genetic Algorithms can improve B2B segment car sales' accuracy when comparing error values in the ordinary Artificial Neural Network and Multiple Linear Regression.
本研究旨在建立一个有效的预测模型,预测汽车产品在B2B细分市场(Business to Business)的销售情况,以获得对未来产品销售的估计。本研究采用多元线性回归和遗传算法优化的人工神经网络。汽车销售的预测因素通常由全国汽车总销量、消费者价格指数、消费者信心指数、通货膨胀率、国内生产总值(GDP)和燃料油价格发布。作者还将调查对象转移到106个决定在公司购买汽车的决策单位(DMU),得出了影响B2B细分市场销售的因素。然后在人工神经网络的训练数据和仿真中评估问卷的结果。将传统人工神经网络与多元线性回归的误差值进行比较,采用遗传算法优化的人工神经网络可以提高B2B细分市场汽车销售的准确率。