Harnessing the Power of Improved Deep Learning for Precise Building Material Price Predictions

Accurate forecasting of construction material prices is essential for effective cost control and risk management in construction projects. However, due to the influence of various complex factors, building material prices exhibit high nonlinearity and instability, often making traditional prediction...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhilong Guo, Yayong Luo, Tongqiang Yi, Xiangnan Jing, Jing Ma
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Buildings
Subjects:
Online Access:https://www.mdpi.com/2075-5309/15/6/873
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850204595301646336
author Zhilong Guo
Yayong Luo
Tongqiang Yi
Xiangnan Jing
Jing Ma
author_facet Zhilong Guo
Yayong Luo
Tongqiang Yi
Xiangnan Jing
Jing Ma
author_sort Zhilong Guo
collection DOAJ
description Accurate forecasting of construction material prices is essential for effective cost control and risk management in construction projects. However, due to the influence of various complex factors, building material prices exhibit high nonlinearity and instability, often making traditional prediction methods inadequate for achieving optimal results. This study introduces an innovative prediction model, CEEMDAN-VMD-GRU-ARIMA, specifically designed for forecasting the price of prestressed steel bars. This model uniquely combines CEEMDAN and VMD to address nonlinear characteristics, and it innovatively incorporates sample entropy for the adaptive selection of either GRU or ARIMA for prediction. Additionally, a VMD decomposition mode number K value optimization method, based on a sparse index, is proposed. Experimental results demonstrate that the model performs exceptionally well, achieving an adjusted R-squared value of 81.10%, with various error indicators significantly surpassing the results for the baseline model. This approach offers new insights for short-term price prediction of building materials and contributes to enhancing the economic benefits and management efficiency of construction projects.
format Article
id doaj-art-670fd886668f4a2ca5c6b30bdd4721f3
institution OA Journals
issn 2075-5309
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Buildings
spelling doaj-art-670fd886668f4a2ca5c6b30bdd4721f32025-08-20T02:11:15ZengMDPI AGBuildings2075-53092025-03-0115687310.3390/buildings15060873Harnessing the Power of Improved Deep Learning for Precise Building Material Price PredictionsZhilong Guo0Yayong Luo1Tongqiang Yi2Xiangnan Jing3Jing Ma4Key Laboratory of Cryospheric Science and Frozen Soil Engineering, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, ChinaNaiman Desertification Research Station, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, ChinaSchool of Power and Mechanical Engineering, Wuhan University, Wuhan 430072, ChinaSchool of Economics and Management, City University of Hefei, Hefei 231137, ChinaDepartment of Psychology, Beijing Normal University, Beijing 100875, ChinaAccurate forecasting of construction material prices is essential for effective cost control and risk management in construction projects. However, due to the influence of various complex factors, building material prices exhibit high nonlinearity and instability, often making traditional prediction methods inadequate for achieving optimal results. This study introduces an innovative prediction model, CEEMDAN-VMD-GRU-ARIMA, specifically designed for forecasting the price of prestressed steel bars. This model uniquely combines CEEMDAN and VMD to address nonlinear characteristics, and it innovatively incorporates sample entropy for the adaptive selection of either GRU or ARIMA for prediction. Additionally, a VMD decomposition mode number K value optimization method, based on a sparse index, is proposed. Experimental results demonstrate that the model performs exceptionally well, achieving an adjusted R-squared value of 81.10%, with various error indicators significantly surpassing the results for the baseline model. This approach offers new insights for short-term price prediction of building materials and contributes to enhancing the economic benefits and management efficiency of construction projects.https://www.mdpi.com/2075-5309/15/6/873construction material price forecastingCEEMDAN-VMD-GRU-ARIMAnonlinear time seriessample entropyprestressed steel bars (PSB)
spellingShingle Zhilong Guo
Yayong Luo
Tongqiang Yi
Xiangnan Jing
Jing Ma
Harnessing the Power of Improved Deep Learning for Precise Building Material Price Predictions
Buildings
construction material price forecasting
CEEMDAN-VMD-GRU-ARIMA
nonlinear time series
sample entropy
prestressed steel bars (PSB)
title Harnessing the Power of Improved Deep Learning for Precise Building Material Price Predictions
title_full Harnessing the Power of Improved Deep Learning for Precise Building Material Price Predictions
title_fullStr Harnessing the Power of Improved Deep Learning for Precise Building Material Price Predictions
title_full_unstemmed Harnessing the Power of Improved Deep Learning for Precise Building Material Price Predictions
title_short Harnessing the Power of Improved Deep Learning for Precise Building Material Price Predictions
title_sort harnessing the power of improved deep learning for precise building material price predictions
topic construction material price forecasting
CEEMDAN-VMD-GRU-ARIMA
nonlinear time series
sample entropy
prestressed steel bars (PSB)
url https://www.mdpi.com/2075-5309/15/6/873
work_keys_str_mv AT zhilongguo harnessingthepowerofimproveddeeplearningforprecisebuildingmaterialpricepredictions
AT yayongluo harnessingthepowerofimproveddeeplearningforprecisebuildingmaterialpricepredictions
AT tongqiangyi harnessingthepowerofimproveddeeplearningforprecisebuildingmaterialpricepredictions
AT xiangnanjing harnessingthepowerofimproveddeeplearningforprecisebuildingmaterialpricepredictions
AT jingma harnessingthepowerofimproveddeeplearningforprecisebuildingmaterialpricepredictions