A novel construction cost prediction model using hybrid natural and light gradient boosting

Chakraborty, Debaditya; Elhegazy, Hosam; Elzarka, Hazem; Gutierrez, Lilianna

doi:10.1016/j.aei.2020.101201

Cited by 99 publications

(26 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Investors avoid adopting machine learning models because of the lack of explainability and dependability. However, the SHAP value method used in this study, combined with the accurate machine learning models, may be used by more experts in making certain real-world decisions ( Chakraborty et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

The effect of green energy, global environmental indexes, and stock markets in predicting oil price crashes: Evidence from explainable machine learning

Jabeur¹,

Khalfaoui

Arfi

2021

Journal of Environmental Management

View full text Add to dashboard Cite

This study aims to predict oil prices during the 2019 novel coronavirus (COVID-19) pandemic by looking into green energy resources, global environmental indexes (ESG), and stock markets. The study employs advanced machine learning, such as the LightGBM, CatBoost, XGBoost, Random Forest (RF), and neural network models. An accurate forecasting framework can effectively capture the trend of the changes in oil prices and reduce the impact of the COVID-19 pandemic on such prices. Additionally, a large dataset with different asset classes was used to investigate the crash period. The research also introduced SHapely Additive exPlanations (SHAP) values for model analysis and interpretability. The empirical results indicate the superiority of the RF and LightGBM over traditional models. Moreover, this new framework provides favorable explanations of the model performance using the efficient SHAP algorithm. It also highlights the core features of predicting oil prices. The study found that high values of GER and ESG lead to lower crude oil prices. Our results are crucial for investors and policymakers in promoting climate change mitigation and sustained economic prosperity through green energy resources.

show abstract

Section: Introductionmentioning

confidence: 99%

The effect of green energy, global environmental indexes, and stock markets in predicting oil price crashes: Evidence from explainable machine learning

Jabeur¹,

Khalfaoui

Arfi

2021

Journal of Environmental Management

View full text Add to dashboard Cite

show abstract

“…LGBM has been used in many domains, such as forecasting the price trend in the cryptocurrency market [40] and cost estimations during the early design phase of construction projects [41], predicting return temperature of district heating systems [42] and prediction of patients' extubation failure for Intensive Care Units [38].…”

Section: ) Regression Prediction Modelsmentioning

confidence: 99%

Human Mobility-Based Features to Analyse the Impact of COVID-19 on Power System Operation of Ireland

Zarbakhsh

Misaghian

McArdle

2022

IEEE Open J. Power Energy

View full text Add to dashboard Cite

are changing human mobility patterns; however, the effects on power systems remain unclear. Previous loads and timings along with weather features are often used in literature as input features in load forecasting, but these may be insufficient during COVID-19. As a result, this paper proposes an analytical framework to assess the impact of COVID-19 on power system operation as well as day-ahead electricity prices in Ireland. To improve peak demand forecasting during pandemics, we incorporate mobility, NPIs, and COVID-19 cases as complementary input features and representative of human behaviour changes. By defining different combinations of these explanatory features, several Machine Learning (ML) algorithms are applied and their performance is compared with the baseline scenario currently used in the literature. Using SHapley Additive Explanations (SHAP), we interpret the best performing model, Light Gradient Boosted Machine, to determine the influence of each feature on the predicted outcomes. We discover that typical load forecasting features still influence ML outcomes the most, but mobility-related changes are also significant. Our finding shows that NPIs impact human behaviour and electricity consumption during times of crisis and can be used in the context of load forecasting to assist policymakers and energy distributors.

show abstract

“…This is done via combining historical information and expert judgement by the project manager (Hashemi et al, 2020). However, this method is questionable, as it assumes a linear relationship between the project cost and its basic design variables such as the location, size, type, and capacity of the structural components (Chakraborty et al, 2020) and doesn't take into account data known at this stage such as payment and procurement methods. Predictive or Statistical estimation methods are also used before design completion relying on the project parameters known at this stage rather than activities relationships and quantities (Son et al, 2019).…”

Section: Modelling Approachesmentioning

confidence: 99%

“…It is a version of ensemble learning, where it consists of a set of decorrelated decision trees to avoid their frequent overfitting issues (Kotu and Deshpande, 2014). Each tree is trained using a bootstrapped sample of the training data (drawn with replacement) on a subset of the parameters that are randomly selected for each tree (Chakraborty, 2020). The final result is predicted for every new record using a majority vote in case of classification or by averaging the predictions for regression tasks, thereby improving the predictive accuracy (Chakraborty, 2020).…”

Section: Random Forest (Rf)mentioning

confidence: 99%

Conceptual estimation of construction duration and cost of public highway projects

Mohamed¹,

Moselhi²

2022

ITcon

View full text Add to dashboard Cite

State Highway Agencies (SHAs) and Departments of Transportation (DOTs) allocate their limited resources to thousands of competing projects in multi-year transportation programs using expert judgement for the expected construction costs and durations. Such estimates overlook influencing parameters known in the planning phase and the importance of building reliable databases to support decision making. Meanwhile, it is possible to generate meaningful predictions in early stages of project development based on historical data gathering and analysis. The present research introduces a newly developed method for conceptual cost and duration estimation for public highway projects utilizing an ensemble of machine learning (ML) models and data collected for projects completed between 2004 and 2015 (roads, bridges, and drainage projects). Unlike previous studies, the proposed method includes project parameters that affect construction durations and costs and were not studied simultaneously before. The parameters considered are facility type, project scope, highway type, length, width, location, level of technical complexity, and new parameters pertinent to payment and procurement methods. The developed method was tested using 29 and 56 randomly selected projects, and the results yielded a Mean Absolute Percentage Error (MAPE) of 7.4% and 4.5% for the duration and cost, respectively, which are lower than the estimation errors of methods reported in recent literature. Additionally, the generalization abilities were assessed by the Mann-Whitney test, and the developed method is found to successfully handle diverse projects. Thus, machine learning models can assist agencies in the review process of competing projects from a high-level management perspective to ultimately develop better management execution programs.

show abstract

A novel construction cost prediction model using hybrid natural and light gradient boosting

Cited by 99 publications

References 33 publications

The effect of green energy, global environmental indexes, and stock markets in predicting oil price crashes: Evidence from explainable machine learning

The effect of green energy, global environmental indexes, and stock markets in predicting oil price crashes: Evidence from explainable machine learning

Human Mobility-Based Features to Analyse the Impact of COVID-19 on Power System Operation of Ireland

Conceptual estimation of construction duration and cost of public highway projects

Contact Info

Product

Resources

About