Ridge Regularization Research Articles

Exploring the Evidence to Interpret Differential Item Functioning via Response Process Data.

Evaluating differential item functioning (DIF) in assessments plays an important role in achieving measurement fairness across different subgroups, such as gender and native language. However, relying solely on the item response scores among traditional DIF techniques poses challenges for researchers and practitioners in interpreting DIF. Recently, response process data, which carry valuable information about examinees' response behaviors, offer an opportunity to further interpret DIF items by examining differences in response processes. This study aims to investigate the potential of response process data features in improving the interpretability of DIF items, with a focus on gender DIF using data from the Programme for International Assessment of Adult Competencies (PIAAC) 2012 computer-based numeracy assessment. We applied random forest and logistic regression with ridge regularization to investigate the association between process data features and DIF items, evaluating the important features to interpret DIF. In addition, we evaluated model performance across varying percentages of DIF items to reflect practical scenarios with different percentages of DIF items. The results demonstrate that the combination of timing features and action-sequence features is informative to reveal the response process differences between groups, thereby enhancing DIF item interpretability. Overall, this study introduces a feasible procedure to leverage response process data to understand and interpret DIF items, shedding light on potential reasons for the low agreement between DIF statistics and expert reviews and revealing potential irrelevant factors to enhance measurement equity.

Predicting State-Level Firearm Suicide Rates: A Machine Learning Approach Using Public Policy Data

IntroductionOver 40,000 people die by suicide annually in the U.S., and firearms are the most lethal suicide method. There is limited evidence on the effectiveness of many state-level policies on reducing firearm suicide. The objective of this study was to identify public policies that best predict state-level firearm suicide rates. MethodsData from the Centers for Disease Control and Prevention's WONDER system and the State Firearm Law Database, a longitudinal catalog of 134 firearm safety laws, were analyzed. The analysis included 1,450 observations from 50 states spanning 1991-2019. An ElasticNet regression technique was used to analyze the relationship between the policy variables and firearm suicide rates. Nested cross-validation was performed to tune the model hyperparameters. The study data were collected and analyzed in 2023 and 2024. ResultsThe optimized ElasticNet approach had a mean MSE of 2.07, which was superior to non-regularized and dummy regressor models. The most influential policies for predicting the firearm suicide rate on average included laws requiring firearm dealers that sell handguns to have a state license and laws requiring individuals to obtain a permit to purchase a firearm through an approval process that includes law enforcement, among others. ConclusionsOn average, firearm suicide rates were lower in state-years that had each influential policy active. Notably, these analyses were ecological and non-causal. However, this study was able to use a supervised machine learning approach with inherent feature selection and many policy types to make predictions using unseen data (i.e., balancing Lasso and Ridge regularization penalties).

Analysis of Logistic Regression Regularization in Wild Elephant Classification with VGG-16 Feature Extraction

The research article explores the intersection of image-based wildlife classification and logistic regression regularization, focusing on the classification of wild elephant species. It begins by highlighting the significance of ecological research in biodiversity monitoring and conservation and introduces Convolutional Neural Networks (CNNs) as potent tools for feature extraction from images. The VGG-16 model is particularly emphasized for its ability to capture hierarchical representations of visual features crucial for classification tasks. The integration of VGG-16 feature extraction with logistic regression regularization is proposed as a compelling approach, offering a balance between sophisticated feature representation and efficient classification algorithms. The literature review delves into image-based wildlife classification, emphasizing the role of CNNs, especially VGG-16, in extracting discriminative features. It discusses the fusion of VGG-16 features with logistic regression and the challenges in this field, such as dataset annotation and environmental variability. The method section outlines the dataset acquisition, feature extraction using the VGG-16 architecture, and model configuration using logistic regression with lasso and ridge regularization. The process of finding the optimal regularization parameter (lambda) and model evaluation through cross-validation is detailed. Results showcase the optimal lambda values for lasso and ridge regularization and compare the performance of logistic lasso and logistic ridge models. Misclassification analysis reveals factors influencing classification accuracy, including feature variability and contextual complexity. The discussion reflects on the implications of the findings, emphasizing the importance of lambda selection and addressing challenges in wildlife classification. It suggests avenues for further research, such as advanced modeling techniques and feature engineering approaches. In conclusion, the study contributes to advancing wildlife classification efforts by leveraging state-of-the-art techniques and sheds light on opportunities to enhance classification accuracy in wildlife conservation.

Cross-domain information fusion and personalized recommendation in artificial intelligence recommendation system based on mathematical matrix decomposition

Given the challenges of inter-domain information fusion and data sparsity in collaborative filtering algorithms, this paper proposes a cross-domain information fusion matrix decomposition algorithm to enhance the accuracy of personalized recommendations in artificial intelligence recommendation systems. The study begins by collecting Douban movie rating data and social network information. To ensure data integrity, Levenshtein distance detection is employed to remove duplicate scores, while natural language processing technology is utilized to extract keywords and topic information from social texts. Additionally, graph convolutional networks are utilized to convert user relationships into feature vectors, and a unique thermal coding method is used to convert discrete user and movie information into binary matrices. To prevent overfitting, the Ridge regularization method is introduced to gradually optimize potential feature vectors. Weighted average and feature connection techniques are then applied to integrate features from different fields. Moreover, the paper combines the item-based collaborative filtering algorithm with merged user characteristics to generate personalized recommendation lists.In the experimental stage, the paper conducts cross-domain information fusion optimization on four mainstream mathematical matrix decomposition algorithms: alternating least squares method, non-negative matrix decomposition, singular value decomposition, and latent factor model (LFM). It compares these algorithms with the non-fused approach. The results indicate a significant improvement in score accuracy, with mean absolute error and root mean squared error reduced by 12.8% and 13.2% respectively across the four algorithms. Additionally, when k = 10, the average F1 score reaches 0.97, and the ranking accuracy coverage of the LFM algorithm increases by 54.2%. Overall, the mathematical matrix decomposition algorithm combined with cross-domain information fusion demonstrates clear advantages in accuracy, prediction performance, recommendation diversity, and ranking quality, and improves the accuracy and diversity of the recommendation system. By effectively addressing collaborative filtering challenges through the integration of diverse techniques, it significantly surpasses traditional models in recommendation accuracy and variety.

Ridge regularization for spatial autoregressive models with multicollinearity issues

Ridge regularization for spatial autoregressive models with multicollinearity issues

Optimizing Matrix Factorization for Personalized Recommendations Using Ridge Regularization

Personalized recommendation systems have become indispensable tools for enhancing user engagement and satisfaction in various online platforms. Matrix Factorization (MF) algorithms serve as fundamental techniques in these systems, allowing for the efficient modeling of user-item interactions and the generation of tailored recommendations. However, ensuring the robustness and generalization capability of MF models remains a challenge, particularly in the presence of sparse and noisy datasets. In this study, we focus on optimizing MF for personalized recommendations through the incorporation of L2 regularization techniques. By introducing a penalty term based on the squared Frobenius norm of the user and item matrices, L2 regularization promotes the learning of more stable and generalized latent representations, thereby mitigating overfitting. We aim to investigate the impact of L2 regularization on recommendation performance and to demonstrate its effectiveness in improving the accuracy and robustness of MF-based recommendation systems. We conduct comprehensive experiments on real-world datasets, evaluating the performance of L2-regularized MF models against baseline approaches. Our results indicate that L2 regularization significantly enhances recommendation accuracy and generalization performance, highlighting its potential to optimize MF for personalized recommendations in diverse application domains

Cognitive reserve, depressive symptoms, obesity, and change in employment status predict mental processing speed and executive function after COVID-19.

The risk factors for post-COVID-19 cognitive impairment have been poorly described. This study aimed to identify the sociodemographic, clinical, and lifestyle characteristics that characterize a group of post-COVID-19 condition (PCC) participants with neuropsychological impairment. The study sample included 426 participants with PCC who underwent a neurobehavioral evaluation. We selected seven mental speed processing and executive function variables to obtain a data-driven partition. Clustering algorithms were applied, including K-means, bisecting K-means, and Gaussian mixture models. Different machine learning algorithms were then used to obtain a classifier able to separate the two clusters according to the demographic, clinical, emotional, and lifestyle variables, including logistic regression with least absolute shrinkage and selection operator (LASSO) (L1) and Ridge (L2) regularization, support vector machines (linear/quadratic/radial basis function kernels), and decision tree ensembles (random forest/gradient boosting trees). All clustering quality measures were in agreement in detecting only two clusters in the data based solely on cognitive performance. A model with four variables (cognitive reserve, depressive symptoms, obesity, and change in work situation) obtained with logistic regression with LASSO regularization was able to classify between good and poor cognitive performers with an accuracy and a weighted averaged precision of 72%, a recall of 73%, and an area under the curve of 0.72. PCC individuals with a lower cognitive reserve, more depressive symptoms, obesity, and a change in employment status were at greater risk for poor performance on tasks requiring mentalprocessing speedand executive function. Study registration: www.ClinicalTrials.gov , identifier NCT05307575.

Estimating Compressional Velocity and Bulk Density Logs in Marine Gas Hydrates Using Machine Learning

Compressional velocity (Vp) and bulk density (ρb) logs are essential for characterizing gas hydrates and near-seafloor sediments; however, it is sometimes difficult to acquire these logs due to poor borehole conditions, safety concerns, or cost-related issues. We present a machine learning approach to predict either compressional Vp or ρb logs with high accuracy and low error in near-seafloor sediments within water-saturated intervals, in intervals where hydrate fills fractures, and intervals where hydrate occupies the primary pore space. We use scientific-quality logging-while-drilling well logs, gamma ray, ρb, Vp, and resistivity to train the machine learning model to predict Vp or ρb logs. Of the six machine learning algorithms tested (multilinear regression, polynomial regression, polynomial regression with ridge regularization, K nearest neighbors, random forest, and multilayer perceptron), we find that the random forest and K nearest neighbors algorithms are best suited to predicting Vp and ρb logs based on coefficients of determination (R2) greater than 70% and mean absolute percentage errors less than 4%. Given the high accuracy and low error results for Vp and ρb prediction in both hydrate and water-saturated sediments, we argue that our model can be applied in most LWD wells to predict Vp or ρb logs in near-seafloor siliciclastic sediments on continental slopes irrespective of the presence or absence of gas hydrate.

A novel kernel ridge grey system model with generalized Morlet wavelet and its application in forecasting natural gas production and consumption

Natural gas production (NGP) and consumption (NGC) always exhibit high nonlinearity, posing challenges for accurate small-sample forecasting. In this work, a novel kernel ridge grey system model with an extended parametric Morlet wavelet (GMW-KRGM) is proposed by integrating the kernel ridge regularization and grey system modelling within a partially linear regression framework and trained by the conjugate gradient method to mitigate the ill-posed problem. Besides, a weighted multi-objective optimization strategy is designed for model hyperparameter optimization and solved by the grey wolf optimizer (GWO). Six real-world NGP and NGC forecasting cases are carried out and empirical results demonstrate that the proposed GMW-KRGM model with optimal hyperparameters solved by GWO always yields superior forecasting performance than the other 2 machine learning models and 7 conventional grey system benchmarks with out-of-sample mean average percentage error (MAPE) improved in 7.4245%–91.8392% and 14.7303%–42.67% on average, respectively and yields more precise forecasting accuracy with fast and stable convergence than the other 5 optimization algorithms with improved MAPE range from 9.5608% to 48.2584%, indicating that the proposed model holds the capability to effectively deal with the nonlinear complex system and has great potential in nonlinear small sample forecasting.

On regression analysis with Padé approximants

The advantages and disadvantages of application of Padé approximants to regression analysis with two independent covariates are discussed. The main difficulty of using Padé function is nonlinearity of data fitting. Possible approaches to overcoming the problem are discussed. New formulation of residuals is suggested in the method of least squares. It leads to a system of linear equations in case of rational functions. The possibility of using ridge regularization technique to avoid overfitting is demonstrated in this approach. To illustrate the efficiency of the suggested method, several practical cases from physics and reliability theory are considered.

Statistical Downscaling of SEVIRI Land Surface Temperature to WRF Near-Surface Air Temperature Using a Deep Learning Model

The analysis of the near-surface air temperature is vital for many applications such as urban heat islands and climate change studies. In particular, extreme weather events are typically localized and so should the corresponding adaptation measures. However, climate scientists are often confronted with the difficulty of providing reliable predictions at high spatial resolutions in the order of 1 km. We propose to train a convolutional neural network model to emulate the hourly high-resolution near-surface air temperature field simulated by the Weather Research and Forecasting (WRF) software over a period of 18 months. The model is driven by current and past lags of coarse SEVIRI land surface temperature fields. This nowcasting application implements a downscaling of the spatial resolution of the input by about a factor of four, while establishing a correlation between current and past land surface temperature maps and the current near-surface air temperature field. The U-Net variant that is proposed in this study uses regularization to prevent over-fitting and implements a novel space-time approach, where multiple time steps are fed into the model through 3D convolution layers. Besides LST, the model also uses urban density as additional static input to be able to predict the temperature more accurately in urban areas and to improve the generalizability of the trained model. The performance of our U-Net model is assessed via comparison to an MLR benchmark (ridge regularization). The model is shown to be superior on all performance metrics. It achieves a mean absolute error of 1.36 °C versus 1.49 °C for benchmark (a 9% relative improvement) and a root mean square error of 1.77 °C versus 1.91 °C for benchmark (a 7% relative improvement). The absolute error of the model is less than 2 °C for 77% of the prediction points versus 72% for the benchmark (a 7% relative improvement). The improvement over the benchmark is even more significant during extreme hot periods. We demonstrate the generalizability of the approach by testing the trained model on unseen spatial domains.

Exploring the ability of vocal biomarkers in distinguishing depression from bipolar disorder, schizophrenia, and healthy controls.

Vocal features have been exploited to distinguish depression from healthy controls. While there have been some claims for success, the degree to which changes in vocal features are specific to depression has not been systematically studied. Hence, we examined the performances of vocal features in differentiating depression from bipolar disorder (BD), schizophrenia and healthy controls, as well as pairwise classifications for the three disorders. We sampled 32 bipolar disorder patients, 106 depression patients, 114 healthy controls, and 20 schizophrenia patients. We extracted i-vectors from Mel-frequency cepstrum coefficients (MFCCs), and built logistic regression models with ridge regularization and 5-fold cross-validation on the training set, then applied models to the test set. There were seven classification tasks: any disorder versus healthy controls; depression versus healthy controls; BD versus healthy controls; schizophrenia versus healthy controls; depression versus BD; depression versus schizophrenia; BD versus schizophrenia. The area under curve (AUC) score for classifying depression and bipolar disorder was 0.5 (F-score = 0.44). For other comparisons, the AUC scores ranged from 0.75 to 0.92, and the F-scores ranged from 0.73 to 0.91. The model performance (AUC) of classifying depression and bipolar disorder was significantly worse than that of classifying bipolar disorder and schizophrenia (corrected p < 0.05). While there were no significant differences in the remaining pairwise comparisons of the 7 classification tasks. Vocal features showed discriminatory potential in classifying depression and the healthy controls, as well as between depression and other mental disorders. Future research should systematically examine the mechanisms of voice features in distinguishing depression with other mental disorders and develop more sophisticated machine learning models so that voice can assist clinical diagnosis better.

Predictive analysis for pathogenicity classification of H5Nx avian influenza strains using machine learning techniques.

Over the past decades, avian influenza (AI) outbreaks have been reported across different parts of the globe, resulting in large-scale economic and livestock loss and, in some cases raising concerns about their zoonotic potential. The virulence and pathogenicity of H5Nx (e.g., H5N1, H5N2) AI strains for poultry could be inferred through various approaches, and it has been frequently performed by detecting certain pathogenicity markers in their haemagglutinin (HA) gene. The utilization of predictive modeling methods represents a possible approach to exploring this genotypic-phenotypic relationship for assisting experts in determining the pathogenicity of circulating AI viruses. Therefore, the main objective of this study was to evaluate the predictive performance of different machine learning (ML) techniques for in-silico prediction of pathogenicity of H5Nx viruses in poultry, using complete genetic sequences of the HA gene. We annotated 2137 H5Nx HA gene sequences based on the presence of the polybasic HA cleavage site (HACS) with 46.33% and 53.67% of sequences previously identified as highly pathogenic (HP) and low pathogenic (LP), respectively. We compared the performance of different ML classifiers (e.g., logistic regression (LR) with the lasso and ridge regularization, random forest (RF), K-nearest neighbor (KNN), Naïve Bayes (NB), support vector machine (SVM), and convolutional neural network (CNN)) for pathogenicity classification of raw H5Nx nucleotide and protein sequences using a 10-fold cross-validation technique. We found that different ML techniques can be successfully used for the pathogenicity classification of H5 sequences with ∼99% classification accuracy. Our results indicate that for pathogenicity classification of (1) aligned deoxyribonucleic acid (DNA) and protein sequences, with NB classifier had the lowest accuracies of 98.41% (+/-0.89) and 98.31% (+/-1.06), respectively; (2) aligned DNA and protein sequences, with LR (L1/L2), KNN, SVM (radial basis function (RBF)) and CNN classifiers had the highest accuracies of 99.20% (+/-0.54) and 99.20% (+/-0.38), respectively; (3) unaligned DNA and protein sequences, with CNN's achieved accuracies of 98.54% (+/-0.68) and 99.20% (+/-0.50), respectively. ML methods show potential for regular classification of H5Nx virus pathogenicity for poultry species, particularly when sequences containing regular markers were frequently present in the training dataset.

Assessment of Machine Learning Methods to Predict Massive Blood Transfusion in Trauma

BackgroundAccurately predicting which patients are most likely to benefit from massive transfusion protocol (MTP) activation may help patients while saving blood products and limiting cost. The purpose of this study is to explore the use of modern machine learning (ML) methods to develop and validate a model that can accurately predict the need for massive blood transfusion (MBT).MethodsThe institutional trauma registry was used to identify all trauma team activation cases between June 2015 and August 2019. We used an ML framework to explore multiple ML methods including logistic regression with forward and backward selection, logistic regression with lasso and ridge regularization, support vector machines (SVM), decision tree, random forest, naive Bayes, XGBoost, AdaBoost, and neural networks. Each model was then assessed using sensitivity, specificity, positive predictive value, and negative predictive value. Model performance was compared to that of existing scores including the Assessment of Blood Consumption (ABC) and the Revised Assessment of Bleeding and Transfusion (RABT).ResultsA total of 2438 patients were included in the study, with 4.9% receiving MBT. All models besides decision tree and SVM attained an area under the curve (AUC) of above 0.75 (range: 0.75–0.83). Most of the ML models have higher sensitivity (0.55–0.83) than the ABC and RABT score (0.36 and 0.55, respectively) while maintaining comparable specificity (0.75–0.81; ABC 0.80 and RABT 0.83).ConclusionsOur ML models performed better than existing scores. Implementing an ML model in mobile computing devices or electronic health record has the potential to improve the usability.

Sketching the Krylov subspace: faster computation of the entire ridge regularization path

We propose a fast algorithm for computing the entire ridge regression regularization path in nearly linear time. Our method constructs a basis on which the solution of ridge regression can be computed instantly for any value of the regularization parameter. Consequently, linear models can be tuned via cross-validation or other risk estimation strategies with substantially better efficiency. The algorithm is based on iteratively sketching the Krylov subspace with a binomial decomposition over the regularization path. We provide a convergence analysis with various sketching matrices and show that it improves the state-of-the-art computational complexity. We also provide a technique to adaptively estimate the sketching dimension. This algorithm works for both the over-determined and under-determined problems. We also provide an extension for matrix-valued ridge regression. The numerical results on real medium and large-scale ridge regression tasks illustrate the effectiveness of the proposed method compared to standard baselines which require super-linear computational time.

A linearization for stable and fast geographically weighted Poisson regression

Although geographically weighted Poisson regression (GWPR) is a popular regression for spatially indexed count data, its development is relatively limited compared to that found for linear geographically weighted regression (GWR), where many extensions (e.g. multiscale GWR, scalable GWR) have been proposed. The weak development of GWPR can be attributed to the computational cost and identification problem in the underpinning Poisson regression model. This study proposes linearized GWPR (L-GWPR) by introducing a log-linear approximation into the GWPR model to overcome these bottlenecks. Because the L-GWPR model is identical to the Gaussian GWR model, it is free from the identification problem, easily implemented, computationally efficient, and offers similar potential for extension. Specifically, L-GWPR does not require a double-loop algorithm, which makes GWPR slow for large samples. Furthermore, we extended L-GWPR by introducing ridge regularization to enhance its stability (regularized L-GWPR). The results of the Monte Carlo experiments confirmed that regularized L-GWPR estimates local coefficients accurately and computationally efficiently. Finally, we compared GWPR and regularized L-GWPR through a crime analysis in Tokyo.

Bandgap energy prediction of senary zincblende III–V semiconductor compounds using machine learning

Two complimentary machine learning (ML) models are developed to estimate the bandgap energy (Eg) of senary zincblende (ZB) III–V semiconductor compounds Alx1Gax2Inx3Py1Asy2Sby3 from molar fractions. The models work – as well – for any compound with smaller number of constituent elements from binaries to quinaries. Some of these compounds exhibit transition between a direct and an indirect Eg as a function of composition. This is due to the fact that the bandgap for this class of materials is either the direct gap at Γ point (EgΓ) or the indirect one between the maximum valance band at Γ point and the minimum conduction band around X point (EgX). Hence, to capture precisely the Eg and its state, the ML models estimate separately the EgΓ and EgX where the lowest energy gap is the effective Eg. For model training, 18 ternary ZB III–V semiconductor compounds are used, which contain all possible ternary configurations of III-type cations (Al, Ga, In) and V-type anions (P, As, Sb). The achieved testing accuracy using cubic regression with ridge regularization – in terms of root mean square error (RMSE) – are 7.583 and 0.021 meV for EgΓ and EgX, respectively. These correspond to R2 of 0.99995 and 1.00000 (8 nines), respectively. To validate the models, they are benchmarked against experimental measurements of four different quaternary ZB III–V semiconductor compounds. The agreement is very noticeable demonstrating the validity and the excellent accuracy of the developed models.

Transfer Learning for Feral Cat Classification Using Logistic Regression

Machine learning is an alternative tool for classifying animal species, especially feral cats. In this research, we use a machine learning algorithm to classify three species of feral cats: American Wildcat, Black-footed Cat, and European Wildcat. We also use a transfer learning model using the VGG-19 network for extracting the features in the feral cat images. By combining the VGG-19 and logistic regression algorithm, we build six models and compare which one is the best to solve the problem. We evaluate and analyze all models using a 5-fold, 10-fold, and 20- fold cross-validation, with accuracy, precision, and recall as the base performance value. The best result obtained is a model with a lasso regularization and cost parameter value of 1, with an accuracy value of 0.846667, a precision value of 0.845389, and a recall value of 0.846667. We also tune the C parameter in each LR model with values such as 0.1, 0.5, and 1. The most optimum C value for the lasso and ridge regularization is one, resulting in an average value of accuracy = 0.813, precision = 0.812, and recall = 0.813.

Machine Learning Method for Fatigue Strength Prediction of Nickel-Based Superalloy with Various Influencing Factors.

The accurate prediction of fatigue performance is of great engineering significance for the safe and reliable service of components. However, due to the complexity of influencing factors on fatigue behavior and the incomplete understanding of the fatigue failure mechanism, it is difficult to correlate well the influence of various factors on fatigue performance. Machine learning could be used to deal with the association or influence of complex factors due to its good nonlinear approximation and multi-variable learning ability. In this paper, the gradient boosting regression tree model, the long short-term memory model and the polynomial regression model with ridge regularization in machine learning are used to predict the fatigue strength of a nickel-based superalloy GH4169 under different temperatures, stress ratios and fatigue life in the literature. By dividing different training and testing sets, the influence of the composition of data in the training set on the predictive ability of the machine learning method is investigated. The results indicate that the machine learning method shows great potential in the fatigue strength prediction through learning and training limited data, which could provide a new means for the prediction of fatigue performance incorporating complex influencing factors. However, the predicted results are closely related to the data in the training set. More abundant data in the training set is necessary to achieve a better predictive capability of the machine learning model. For example, it is hard to give good predictions for the anomalous data if the anomalous data are absent in the training set.

When are Google Data Useful to Nowcast GDP? An Approach via Preselection and Shrinkage

ABSTRACT Alternative datasets are widely used for macroeconomic nowcasting together with machine learning–based tools. The latter are often applied without a complete picture of their theoretical nowcasting properties. Against this background, this article proposes a theoretically grounded nowcasting methodology that allows researchers to incorporate alternative Google Search Data (GSD) among the predictors and that combines targeted preselection, Ridge regularization, and Generalized Cross Validation. Breaking with most existing literature, which focuses on asymptotic in-sample theoretical properties, we establish the theoretical out-of-sample properties of our methodology and support them by Monte Carlo simulations. We apply our methodology to GSD to nowcast GDP growth rate of several countries during various economic periods. Our empirical findings support the idea that GSD tend to increase nowcasting accuracy, even after controlling for official variables, but that the gain differs between periods of recessions and of macroeconomic stability.