Forecasting gold price with the XGBoost algorithm and SHAP interaction values

Jabeur, Sami Ben; Mefteh‐Wali, Salma; Viviani, Jean‐Laurent

doi:10.1007/s10479-021-04187-w

Cited by 90 publications

(41 citation statements)

References 93 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The XGBoost algorithm is a gradient boosting, gradient lifting method that uses an addition model and a forward distribution algorithm to gradually approach the optimal result. Moreover, the XGBoost algorithm simultaneously prevents model overfitting by introducing a regularization term (a measure of tree model complexity) in the objective function [ 63 ], which is calculated as follows:

where

is the generated tree,

is the newly created tree model and N is the total number of tree models. In this study, the ESVs of the study area were used as dependent variables, and various natural and social factors were used as independent variables.…”

Section: Methodsmentioning

confidence: 99%

Ecosystem Service Values in the Dongting Lake Eco-Economic Zone and the Synergistic Impact of Its Driving Factors

Chen

Zhang

et al. 2022

IJERPH

View full text Add to dashboard Cite

Ecosystem service values (ESVs) are crucial to ecological conservation and restoration, urban and rural planning, and sustainable development of land. Therefore, it is important to study ESVs and their driving factors in the Dongting Lake Eco-Economic Zone (Dongting Lake). This paper quantifies the changes in ESVs in the Dongting Lake using land use data from 2000, 2005, 2010 and 2018. The eXtreme Gradient Boosting (XGBoost) model is used to study the effects of individual driving factors and the synergistic effects of these driving factors on ESVs. Our analysis suggests that: (1) From 2000 to 2018, the largest dynamic degree values in the Dongting Lake are in unused land types, followed by construction lands and wetlands. The ESVs of the Dongting Lake show an increasing trend, with those of forestlands being the highest, accounting for approximately 44.65% of the total value. Among the ESVs functions, water containment, waste treatment, soil formation and protection, biodiversity conservation and climate regulation contribute the most to ESVs, with a combined contribution of 76.64% to 76.99%; (2) The integrated intensity of anthropogenic disturbance shows a U-shaped spatial distribution, decreasing from U1 to U3. The driving factors in descending order of importance are the human impact index, total primary productivity (GPP), slope, elevation, population, temperature, gross domestic product, precipitation and PM2.5; (3) When the GPP is low (GPP < 900), the SHAP (SHapley Additive exPlanation) value of the high human impact index is greater than zero, indicating that an increase in GPP increases the ESVs in the Dongting Lake. This study can provide technical support and a theoretical basis for ecological environmental protection and ecosystem management in the Dongting Lake.

show abstract

where

is the generated tree,

Section: Methodsmentioning

confidence: 99%

Ecosystem Service Values in the Dongting Lake Eco-Economic Zone and the Synergistic Impact of Its Driving Factors

Chen

Zhang

et al. 2022

IJERPH

View full text Add to dashboard Cite

show abstract

“…XGBoost is an ML technique developed by Ostrowski and Birman ( 2006 ) that can be used for regression and classification problems. This method has been adopted in different domains, such as healthcare (Singh et al, 2019 ) and the metal market (Ben Jabeur et al, 2021a , 2021b ).…”

Section: Methodsmentioning

confidence: 99%

“…Table 1 reports several studies that used advanced ML models to predict crude oil prices. For example, Ben Jabeur et al, ( 2021a , 2021b ) attempted to predict oil prices during the COVID-19 pandemic. To this end, they used advanced ML methods such as LightGBM, CatBoost, XGBoost, random forest (RF), and neural network models.…”

Section: Literature Reviewmentioning

confidence: 99%

“…They indicated that the XGBoost method has a higher ability in terms of learning speed and performance compared to other machine learning (ML) tools. It has become more robust to provide good and accurate forecasts and to reduce complexity, especially when data normalization is applied (Ben Jabeur et al, 2021a , 2021b ). The notable motivations behind the use of XGBoost soft-computing tools to forecast crude oil prices are as follows.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Do Gas Price and Uncertainty Indices Forecast Crude Oil Prices? Fresh Evidence Through XGBoost Modeling

et al. 2022

View full text Add to dashboard Cite

This study examines the forecasting power of the gas price and uncertainty indices for crude oil prices. The complex characteristics of crude oil price such as a non-linear structure, time-varying, and non-stationarity motivate us to use a newly proposed approach of machine learning tools called XGBoost Modelling. This intelligent tool is applied against the SVM and ARIMAX (p,d,q) models to assess the complex relationships between crude oil prices and their forecasters. Empirical evidence shows that machine learning models, such as the SVM and XGBoost models, dominate traditional models, such as ARIMAX, to provide accurate forecasts of crude oil prices. Performance assessment reveals that the XGBoost model displays superior prediction capacity over the SVM model in terms of accuracy and convergence. The superior performance of XGBoost is due to its lower complexity and costs, high accuracy, and rapid processing times. The feature importance analysis conducted by the Shapley additive explanation method (SHAP) highlights that the different uncertainty indexes and the gas price display a significant ability to forecast future WTI crude prices. Additionally, the SHAP values suggest that the oil implied volatility captures valuable forecasting information of gas prices and other uncertainty indices that affect the WTI crude oil price.

show abstract

“…For validating the proposed FI techniques, this study utilized the SHAP (SHapley Additive exPlanations), a cutting-edge methodology for explaining the output of machine learning models by measuring the contribution of each input feature to the predicted output value (Lundberg and Lee 2017). The SHAP values have been widely used to measure the importance of features in various domains, such as gold price prediction (Jabeur et al 2021), online review (Meng et al 2021), COVID-19 diagnosis (Zoabi et al 2021), and traumatic brain injury prognostication (Farzaneh et al 2021). Effrosynidis and Arampatzis (2021) examined the consistency and effectiveness of various feature selection techniques in environmental datasets and demonstrated SHAP's excellence.…”

Section: Introductionmentioning

confidence: 99%

A Deep Neural Network Architecture to Model Reference Evapotranspiration Using a Single Input Meteorological Parameter

2021

View full text Add to dashboard Cite

Hydro-agrological research considers the reference evapotranspiration (ETo), driven by meteorological variables, crucial for achieving precise irrigation in precision agriculture. ETo modelling based on a single meteorological parameter would be beneficial in places where the collection of climatic parameters is challenging. The aim of this research is to develop a deep neural network (DNN) architecture that predicts daily ETo with a single input parameter selected based on the feature importance (FI) score generated by the machine learning techniques, random forest (RF), and extreme gradient boosting (XGBoost). This study also investigated the potential of SHapley Additive exPlanations to interpret and validate the outcomes of the feature selection methods by assessing the contributions of each feature to the ETo prediction. These methods recommended solar radiation as a significant parameter in the datasets of three California Irrigation Management System (CIMIS) weather stations located in distinct ETo zones. Three ETo models (DNN-Ret, XGB-Ret, and RF-Ret) were built using solar radiation as the sole input, and CIMIS ETo as the output. The performance evaluation of the developed models proved that DNN-Ret outperformed XGB-Ret and RF-Ret regardless of the dataset, with coefficients of determination (R 2 ) ranging from 0.914 to 0.954 in the local scenario, with an average decrease of 8–9.5% in mean absolute error and root mean squared error, and an improvement of 2.6–2.9% in Nash–Sutcliffe efficiency and 1.7–2% increase in R 2 . The overall result analysis highlighted the efficiency of DNN-Ret in the single input parameter based ETo modelling in diverse climatic zones.

show abstract

Forecasting gold price with the XGBoost algorithm and SHAP interaction values

Cited by 90 publications

References 93 publications

Ecosystem Service Values in the Dongting Lake Eco-Economic Zone and the Synergistic Impact of Its Driving Factors

Ecosystem Service Values in the Dongting Lake Eco-Economic Zone and the Synergistic Impact of Its Driving Factors

Do Gas Price and Uncertainty Indices Forecast Crude Oil Prices? Fresh Evidence Through XGBoost Modeling

A Deep Neural Network Architecture to Model Reference Evapotranspiration Using a Single Input Meteorological Parameter

Contact Info

Product

Resources

About