In general, preliminary or primary cost estimates are used to select contractors from among bidders in Japan. The primary cost estimate must be accurate, otherwise the contractor selected from the bidding process will lose profit. A general contractor in the world does not have a super-skilled engineer who can achieve the accurate primary cost estimates. The conventional primary estimate has a high error range and low reliability. An automated system converting detailed estimates to primary estimates has been highly demanded in the world. This paper presents a prototype AI converter that can accurately and automatically convert detailed cost estimates into primary estimates. Converting detailed cost estimates to primary estimates lies in a regression problem. This paper proposes a feature-elimination based data augmentation method for regression problems. The empirical experiment shows that the proposed data augmentation method is quite effective with an Extra-Trees ensemble method. The proposed method was empirically examined by using Colorado Department of Transportation (CDOT) dataset for accurately predicting constructions costs with the Extra-Trees algorithm and random forest algorithm respectively. The CDOT dataset is one and only one of the largest datasets available in public for constructions costs quotation/estimation of roads, bridges and buildings.

一般而言，初步或初级成本估算用于从日本的投标人中选择承包商。初步成本估算必须准确，否则从招标过程中选择的承包商将损失利润。世界上的总承包商没有一个超级熟练的工程师可以做到准确的初级成本估算。传统的初步估计具有较大的误差范围和较低的可靠性。世界上非常需要一种将详细估算转换为初步估算的自动化系统。本文介绍了一种原型 AI 转换器，可以准确自动地将详细的成本估算转换为初步估算。将详细成本估算转换为主要估算存在于回归问题中。本文针对回归问题提出了一种基于特征消除的数据增强方法。实证实验表明，所提出的数据增强方法对于 Extra-Trees 集成方法非常有效。通过使用科罗拉多州交通部 (CDOT) 数据集对所提出的方法进行了实证检验，分别使用 Extra-Trees 算法和随机森林算法准确预测施工成本。CDOT 数据集是公共可用的最大的数据集之一，也是唯一一个用于道路、桥梁和建筑物的建筑成本报价/估算。通过使用科罗拉多州交通部 (CDOT) 数据集对所提出的方法进行了实证检验，分别使用 Extra-Trees 算法和随机森林算法准确预测施工成本。CDOT 数据集是公共可用的最大的数据集之一，也是唯一一个用于道路、桥梁和建筑物的建筑成本报价/估算。通过使用科罗拉多州交通部 (CDOT) 数据集对所提出的方法进行了实证检验，分别使用 Extra-Trees 算法和随机森林算法准确预测施工成本。CDOT 数据集是公共可用的最大的数据集之一，也是唯一一个用于道路、桥梁和建筑物的建筑成本报价/估算。