Spatial Prediction of Apartment Rent using Regression-Based and Machine Learning-Based Approaches with a Large Dataset
Spatial Prediction of Apartment Rent using Regression-Based and Machine Learning-Based Approaches with a Large Dataset
复制标题
DOI：
10.1007/s11146-022-09929-6
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Takahiro Yoshida;D. Murakami;H. Seya
中科院分区：
文献类型：
--
作者：
Takahiro Yoshida;D. Murakami;H. Seya
本研究采用大数据集（最多n = 106），通过增加新的经验证据并考虑观察结果的空间依赖性，试图增强回归和基于机器学习的租金价格预测模型之间的比较文献。基于回归的方法结合了最近邻高斯过程（NNGP）模型，使克里金应用于大型数据集。相比之下，基于机器学习的方法利用了典型的模型：极端梯度提升（XGBoost），随机森林（RF）和深度神经网络（DNN）。使用日本公寓租金数据比较了这些模型的样本外预测准确性，样本大小顺序不同（即，n= 104，105，106）。结果表明，随着样本量的增加，XGBoost和RF优于NNGP，具有更高的样本外预测精度。XGBoost在对数和真实的尺度上对所有样本量和误差度量以及所有价格段都实现了最高的预测准确度，前提是租金的分布在训练和测试数据中相似。几种方法的比较，占RF的空间依赖性表明，简单地添加空间坐标的解释变量可能是足够的。
Employing a large dataset (at most, the order ofn= 106), this study attempts enhance the literature on the comparison between regression and machine learning-based rent price prediction models by adding new empirical evidence and considering the spatial dependence of the observations. The regression-based approach incorporates the nearest neighbor Gaussian processes (NNGP) model, enabling the application of kriging to large datasets. In contrast, the machine learning-based approach utilizes typical models: extreme gradient boosting (XGBoost), random forest (RF), and deep neural network (DNN). The out-of-sample prediction accuracy of these models was compared using Japanese apartment rent data, with a varying order of sample sizes (i.e.,n= 104, 105, 106). The results showed that, as the sample size increased, XGBoost and RF outperformed NNGP with higher out-of-sample prediction accuracy. XGBoost achieved the highest prediction accuracy for all sample sizes and error measures in both logarithmic and real scales and for all price bands if the distribution of rents is similar in training and test data. A comparison of several methods to account for the spatial dependence in RF showed that simply adding spatial coordinates to the explanatory variables may be sufficient.