arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12300econ.GNcs.CYq-fin.EC
收藏

基于印尼电子商务数据的房地产企业分类模型

Property Business Classification Model Based on Indonesia E-Commerce Data

Andry Alamsyah, Fariz Denada Sudrajat, Herry Irawan

摘要:

在线房地产业务或称为电子商务目前正在经历房屋销售的增长。印尼的电子商务房地产业务有积极的趋势,从2011年到2015年销售额增长超过500%。物业价格的预测对帮助投资者或公众在购买物业之前获得准确信息非常重要。预测方法之一是基于几个独特的房地产行业属性进行分类,例如建筑物大小,土地大小,房间数量和位置。今天,数据很容易获得,有许多来自电子商务网站的开放数据。电子商务包含有关房屋和其他房产的信息。人们还经常访问该网站,以找到合适的房产或使用价格信息出售房产,这些信息共同作为开放数据提供。为了预测房地产销售量,本研究采用了数据挖掘中两种不同的分类方法:决策树分类法和k-NN分类法。我们比较了哪种模型分类更好地预测房地产价格及其属性。我们使用印度尼西亚最大的基于房地产的电子商务网站Rumah123.com作为我们的开放数据源,并选择在我们的实验地点万隆。决策树的准确率为75%,KNN为71%,而且k-NN比决策树能发现更多的数据模式。

英文摘要:

Online property business or known as e-commerce is currently experiencing an increase in home sales. Indonesia's e-commerce property business has positive trending shown by the increasing sales of more than 500% from 2011 to 2015. A prediction of the property price is important to help investors or the public to have accurate information before buying property. One of the methods for prediction is a classification based on several distinctive property industry attributes, such as building size, land size, number of rooms, and location. Today, data is easily obtained, there are many open data from E-commerce sites. E-commerce contains information about homes and other properties advertised to sell. People also regularly visit the site to find the right property or to sell the property using price information which collectively available as open data. To predict the property sales, this research employed two different classification methods in Data Mining which are Decision Tree and k-NN classification. We compare which model classification is better to predict property price and their attributes. We use Indonesia's biggest property-based e-commerce site Rumah123.com as our open data source, and choose location Bandung in our experiment. The accuracy result of the decision tree is 75% and KNN is 71%, other than that k-NN can explore more data patterns than the Decision Tree.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑