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.

中文翻译：

---

基于印尼电子商务数据的物业业务分类模型

在线房地产业务或称为电子商务的房屋销售目前正在增长。印度尼西亚的电子商务房地产业务呈积极趋势，2011年至2015年的销售额增长超过500％。对房地产价格的预测对于帮助投资者或公众在购买房地产之前获得准确的信息非常重要。一种预测方法是基于房地产行业的几个独特属性进行分类，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，电子商务网站上有许多开放数据。电子商务包含有关出售的房屋和其他财产的信息。人们还定期访问该站点以找到合适的财产或使用价格信息（以公开数据的形式共同出售）出售该财产。为了预测房地产销售，本研究在数据挖掘中采用了两种不同的分类方法，即决策树和k-NN分类。我们比较哪种模型分类更适合预测房地产价格及其属性。我们使用印度尼西亚最大的房地产电子商务网站Rumah123.com作为开放数据源，并在实验中选择万隆位置。决策树的准确性结果为75％，KNN为71％，除了k-NN可以探索比决策树更多的数据模式。我们比较哪种模型分类更适合预测房地产价格及其属性。我们使用印度尼西亚最大的房地产电子商务网站Rumah123.com作为开放数据源，并在实验中选择万隆位置。决策树的准确性结果为75％，KNN为71％，除了k-NN可以探索比决策树更多的数据模式。我们比较哪种模型分类更适合预测房地产价格及其属性。我们使用印度尼西亚最大的房地产电子商务网站Rumah123.com作为开放数据源，并在实验中选择万隆位置。决策树的准确性结果为75％，KNN为71％，除了k-NN可以探索比决策树更多的数据模式。