{"title":"基于线性回归的房价预测","authors":"Noviyanti T M Sagala, Laura Hestia Cendriawan","doi":"10.1109/ICCED56140.2022.10010684","DOIUrl":null,"url":null,"abstract":"Property entrepreneurs will compete to build properties, especially houses for investment facilities. This will make house prices increase day by day with a high purchasing power of the people. Consumers will think in buying a house whether the house they buy will have a good profit value or not. The aim of the study is to build a model that may predict house price for company and become a business decision for consumers. The methodology used seven major steps namely, business understanding, data understanding, data cleaning, data standardization, modelling, and evaluation. This study develop a linear regression model for home price prediction and tests it using data from the Maribelajar company. These are carried out on the Azure Platform by creating two pipelines. One pipeline for training and another for testing. The results are then visualized using Power Business Intelligence for providing a proper business performance analysis. From the experimental results, the model achieved RMSE= 0.0334 and R coefficient = 0.7. The data analysis and testing in this study show that the multiple linear regression model can forecast and evaluate housing prices to some extent, but the algorithm may still be improved using more advanced machine learning approaches.","PeriodicalId":200030,"journal":{"name":"2022 IEEE 8th International Conference on Computing, Engineering and Design (ICCED)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"House Price Prediction Using Linier Regression\",\"authors\":\"Noviyanti T M Sagala, Laura Hestia Cendriawan\",\"doi\":\"10.1109/ICCED56140.2022.10010684\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Property entrepreneurs will compete to build properties, especially houses for investment facilities. This will make house prices increase day by day with a high purchasing power of the people. Consumers will think in buying a house whether the house they buy will have a good profit value or not. The aim of the study is to build a model that may predict house price for company and become a business decision for consumers. The methodology used seven major steps namely, business understanding, data understanding, data cleaning, data standardization, modelling, and evaluation. This study develop a linear regression model for home price prediction and tests it using data from the Maribelajar company. These are carried out on the Azure Platform by creating two pipelines. One pipeline for training and another for testing. The results are then visualized using Power Business Intelligence for providing a proper business performance analysis. From the experimental results, the model achieved RMSE= 0.0334 and R coefficient = 0.7. The data analysis and testing in this study show that the multiple linear regression model can forecast and evaluate housing prices to some extent, but the algorithm may still be improved using more advanced machine learning approaches.\",\"PeriodicalId\":200030,\"journal\":{\"name\":\"2022 IEEE 8th International Conference on Computing, Engineering and Design (ICCED)\",\"volume\":\"42 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-07-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 IEEE 8th International Conference on Computing, Engineering and Design (ICCED)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCED56140.2022.10010684\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 8th International Conference on Computing, Engineering and Design (ICCED)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCED56140.2022.10010684","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
房地产企业家将竞相建造房产,尤其是用于投资设施的住房。这将使房价日益上涨,人们的购买力很高。消费者在买房子的时候会考虑他们买的房子是否有良好的利润价值。本研究的目的是建立一个可以预测公司房价的模型,并成为消费者的商业决策。该方法使用了七个主要步骤,即业务理解、数据理解、数据清理、数据标准化、建模和评估。本文建立了一个线性回归模型用于房价预测,并使用Maribelajar公司的数据对其进行了检验。这些都是在Azure平台上通过创建两个管道来实现的。一个用于培训,另一个用于测试。然后使用Power Business Intelligence将结果可视化,以提供适当的业务性能分析。从实验结果来看,该模型的RMSE= 0.0334, R系数= 0.7。本研究的数据分析和测试表明,多元线性回归模型可以在一定程度上预测和评估房价,但算法仍然可以使用更先进的机器学习方法进行改进。
Property entrepreneurs will compete to build properties, especially houses for investment facilities. This will make house prices increase day by day with a high purchasing power of the people. Consumers will think in buying a house whether the house they buy will have a good profit value or not. The aim of the study is to build a model that may predict house price for company and become a business decision for consumers. The methodology used seven major steps namely, business understanding, data understanding, data cleaning, data standardization, modelling, and evaluation. This study develop a linear regression model for home price prediction and tests it using data from the Maribelajar company. These are carried out on the Azure Platform by creating two pipelines. One pipeline for training and another for testing. The results are then visualized using Power Business Intelligence for providing a proper business performance analysis. From the experimental results, the model achieved RMSE= 0.0334 and R coefficient = 0.7. The data analysis and testing in this study show that the multiple linear regression model can forecast and evaluate housing prices to some extent, but the algorithm may still be improved using more advanced machine learning approaches.