Application Of Machine Learning Models Research Articles

DelayDetect: Pre-takeoff Delay Anticipation

Abstract: Flight delays pose significant challenges to both passengers and airlines, leading to inconvenience, financial losses, and operational disruptions. A comprehensive system is introduced to address the issue of airline flight delays through the application of machine learning models. Leveraging comprehensive datasets encompassing historical flight records, meteorological data, airport congestion patterns and other variables, this model aims to construct predictive models capable of accurately forecasting the probability of flight delays. Various machine learning methodologies including random forests and regression models, are systematically examined in this predictive task. Performance evaluation is conducted employing established metrics such as accuracy and precision. In conclusion, flight delay anticipation is a valuable tool that can revolutionize the aviation industry by minimizing disruptions, reducing costs, and increasing passenger satisfaction.

Machine Learning Models for Parkinson Disease: Systematic Review.

With the increasing availability of data, computing resources, and easier-to-use software libraries, machine learning (ML) is increasingly used in disease detection and prediction, including for Parkinson disease (PD). Despite the large number of studies published every year, very few ML systems have been adopted for real-world use. In particular, a lack of external validity may result in poor performance of these systems in clinical practice. Additional methodological issues in ML design and reporting can also hinder clinical adoption, even for applications that would benefit from such data-driven systems. To sample the current ML practices in PD applications, we conducted a systematic review of studies published in 2020 and 2021 that used ML models to diagnose PD or track PD progression. We conducted a systematic literature review in accordance with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines in PubMed between January 2020 and April 2021, using the following exact string: "Parkinson's" AND ("ML" OR "prediction" OR "classification" OR "detection" or "artificial intelligence" OR "AI"). The search resulted in 1085 publications. After a search query and review, we found 113 publications that used ML for the classification or regression-based prediction of PD or PD-related symptoms. Only 65.5% (74/113) of studies used a holdout test set to avoid potentially inflated accuracies, and approximately half (25/46, 54%) of the studies without a holdout test set did not state this as a potential concern. Surprisingly, 38.9% (44/113) of studies did not report on how or if models were tuned, and an additional 27.4% (31/113) used ad hoc model tuning, which is generally frowned upon in ML model optimization. Only 15% (17/113) of studies performed direct comparisons of results with other models, severely limiting the interpretation of results. This review highlights the notable limitations of current ML systems and techniques that may contribute to a gap between reported performance in research and the real-life applicability of ML models aiming to detect and predict diseases such as PD.

Pharmaceutical Supply Chain Management

Supply chain management (SCM) refers to the coordination and oversight of all activities involved in the production, procurement, transformation, and delivery of goods or services from the point of origin to the point of consumption. It encompasses the planning, execution, and control of various processes involved in the flow of materials, information, and finances across the entire supply chain. In this paper, the authors have done a detailed analysis of the pharmaceutical dataset and predicted useful metrics that can be used in the shipping industry. This paper aims to demonstrate the application of machine learning models on the prediction of shipping mode. The model is trained on various features of the pharmaceutical supply chain dataset such as unit price, first-line designation, and delivery dates. Data cleaning and feature engineering were done and multiple models were trained. Out of the models tested, XGboost was found to give the best results for the prediction of weight, shipment modes and delivery date. Key Words: Supply chain management, Machine Learning models, Shipping Industry, XG Boost

Estimating nonlinear wind-induced response of roof cable nets by aeroelastic experiments and ML modeling

The paper examines the structural engineering challenges related to the assessment of the wind-induced vertical displacements of lightweight, hyperbolic-paraboloid cable-supported membrane roofs. Analysis and comparisons are conducted using three distinct methods for calculating the roof vertical, out-of-plane displacements. Finite element method (FEM) analysis is employed using: (i) estimated static nodal forces obtained from wind pressure coefficients determined by aerodynamic wind tunnel tests on a rigid building model, and (ii) loads found from wind pressure coefficients, estimated through machine learning (ML) methods, and (iii) measured roof response found from aeroelastic wind tunnel tests on a flexible model. The study examines three different roof geometries (square, rectangular and circular) and two distinct membrane curvatures for each geometry. Furthermore, wind directionality (three mean-wind incidence angles) and Reynolds number effects (seven mean wind velocities) are studied. Comparisons show that the non-linear FEM analysis, based on estimated static wind loads, underestimates the roof displacements at the roof center, compared to the direct measurements on the aeroelastic model. The main contribution of the study consists of a novel application of ML models, and Artificial Neural Networks (ANNs) in particular, which are employed to correct roof displacement estimations, found by simplified aerodynamic test pressure measurements on rigid roof models. The goal is to better describe the complex fluid-structure interaction of the roof membranes, which can only be achieved by direct aeroelastic tests that are difficult to design and execute. Finally, the study demonstrates that ANNs can be used not only for the preliminary design of the full-scale structure but also for construction of wind tunnel scale models.

Advanced hybrid numerical-machine learning computational study on fluid flow modeling in magnetic nanocarriers for targeted drug delivery

Development of comprehensive models for simulation of blood flow containing magnetic nanoparticles is of fundamental importance due to its application in medical science and cancer treatment. Owing to the complexity of the process, advanced hybrid models are preferred over conventional models. The focus of this study is on the application of machine learning models for predicting velocity in a given dataset to study the fluid flow in vessel containing magnetic nanocarrier for targeted cancer therapy. The numerical model was performed to simulate the blood flow through vessel, while the output data was used in developing machine learning models. The dataset is utilized to train three distinct models: Random Forest, Extra Tree, and AdaBoost Decision Tree. The hyper-parameter optimization is carried out via the Whale Optimization Algorithm (WOA) to improve the models' predictive capabilities. The dataset encompasses more than 17 thousand rows of data. The findings demonstrate the effectiveness of the suggested methodology, as evidenced by the impressive performance metrics exhibited by each model. The Random Forest model achieved a high R-squared value of 0.98768, indicating a robust fit to the data. The Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) for Random Forest were recorded at 6.1223E-04 and 6.09246, respectively. Similarly, the Extra Tree model exhibited superior predictive accuracy with a score of 0.99151 with R-squared metric, showcasing its skill in uncovering the fundamental patterns present in the dataset. The associated RMSE and MAPE for Extra Tree were notably low at 5.1682E-04 and 1.20955E-01, respectively. The AdaBoost Decision Tree model exhibited notable efficacy, as evidenced by its R-squared score of 0.96944, albeit marginally lower than the other models. The RMSE and MAPE for AdaBoost DT were reported at 9.1863E-04 and 8.06333, respectively.

Deciphering and predicting changes in antibiotic resistance genes during pig manure aerobic composting via machine learning model.

Livestock manure is one of the most important pools of antibiotic resistance genes (ARGs) in the environment. Aerobic composting can effectively reduce the spread of antibiotic resistance risk in livestock manure. Understanding the effect of aerobic composting process parameters on manure-sourced ARGs is important to control their spreading risk. In this study, the effects of process parameters on ARGs during aerobic composting of pig manure were explored through data mining based on 191 valid data collected from literature. Machine learning (ML) models (XGBoost and Random Forest) were utilized to predict the rate of ARGs changes during pig manure composting. The model evaluation index of the XGBoost model (R2 = 0.651) was higher than that of the Random Forest (R2 = 0.490), indicating that XGBoost had better prediction performance. Feature importance was further calculated for the XGBoost model, and the XGBoost black box model was interpreted by Shapley additive explanations analysis. Results indicated that the influencing factors on the ARGs variation in pig manure were sequentially divided into thermophilic period, total composting period, composting real time, and thermophilic stage average temperature. The findings gave an insight into the application of ML models to predict and decipher the ARG changes during manure composting and provided suggestions for better composting manipulation and optimization of process parameters.

Classification for Dividend Payout in Vietnam Stock Exchange Market: A Comparative Review of Machine Learning Algorithms

This study explores the application of machine learning models to predict dividend payouts for publicly listed companies in the Vietnamese stock market. The authors compared various machine learning algorithms to identify the most suitable one for this task. Based on our evaluation, the test shows that the Random Forest algorithm outperformed other methods in terms of accuracy, F1 score, and time efficiency. Furthermore, we analyzed the feature’s importance to understand the key factors driving dividend payouts. The results can help investors, managers, and government agencies make informed decisions and improve financial market transparency. The study also highlights the potential of using machine learning algorithms to automate and enhance the credit rating process, leading to more accurate and real-time assessments of business creditworthiness in Vietnam.

A Comparative study of the Envisaged and Definite Stock Prices of BSE SMEs Using RNN during the COVID-19 Pandemic

The stock market is unstable, but the use of machine learning algorithms allows to predict its future dynamics before spending. The most popular area of scientific research right nowadays is machine learning, which involves enabling computers to perform tasks that often require human intelligence. The purpose of this paper is to construct a model using a network of Long-Short Term Memory model (LSTM) to forecast future stock market values. The paper presents the advantages and disadvantages of machine learning for assessing and forecasting the stock market. A review of literature on the application of machine learning models in key areas of finance using methodological model assessment and data manipulation is also available. This paper focuses on the losses of the SME sector due to COVID-19 by doing a comparative study using secondary data collection between the predicted closed stock prices and actual stock prices of the BSE SME IPO index for the period from 1 January 2018 to 30 April 2021.The LSTM network of Recurrent Neural Networks (RNNs) most effective deep learning model, is used to predict stock prices. The study provides insight and direction on where lockdown has a massive impact on the stock prices of BSE SME IPOs. The authors developed a model for predicting the future value of stock in the market, the application of which gave some positive results, demonstrating the need for machine learning and how it can change the world of finance. The novelty of the study is that in India, machine learning and deep learning methods in the field of finance are used much less often than in other countries.

Machine learning-based modeling of variable compression ratio engine performance and emissions with JME-ZnO nanoemulsion

ABSTRACT Diesel engines fueled with nanoemulsion of biodiesel and diesel have shown promising results in reducing emissions without significant engine problems. However, the evaluation of the impact of biodiesel-nano emulsion on engine performance and exhaust emissions requires time-consuming and costly experimental testing. Modelling simulations have gained attention as a useful approach to overcome these challenges. Artificial intelligence (AI) has an extensive variety of applications in various domains, including energy systems. By training computers using machine learning (ML), they can make better decisions and outperform humans. AI-based models offer promising prospects in energy generation predictions. However, these prediction models can be computationally demanding. In this paper, the authors propose a Boosting-based Multi-Target Regression model using ML techniques to predict the pursuance and exhaust of a diesel engine. The study aims to advance the understanding of enhanced engine performance through the application of ML models. The MTXGB model demonstrates high average accuracy (high R2-score of 0.9989) and low error rates of 0.0123 for all six targets.

Predicting shear strength in UHPC beams through an innovative neural network with SHAP interpretation

Ultra-High performance concrete (UHPC) has garnered considerable attention in the construction industry due to its exceptional mechanical properties and durability. In the design of UHPC beams, accurately predicting shear strength is crucial. Inspired by the dense blocks in DenseNet, this paper proposes a novel neural network for predicting the shear strength of UHPC beams. A comprehensive database of UHPC beams was initially established through extensive literature data collection, amassing 619 experimental data samples. Preprocessing was subsequently conducted using mahalanobis distance (DM) to eliminate outliers. Subsequently, the database underwent detailed parameter analysis. In practical testing, the novel neural network model exhibited superior accuracy in predicting the shear strength of UHPC beams, surpassing traditional machine learning (ML) models and empirical formulas. Furthermore, it demonstrated excellent generalization capabilities, achieving an R2 value of 0.988 in the training set and 0.964 in the test set. The study introduced the shapley additive explanations (SHAP) method to conduct global and local interpretability analysis of the network model, demonstrating the contributions of each input parameter to the model predictions. Finally, based on this network model, a graphical user interface (GUI) was developed for researchers engaged in UHPC beam design, enabling users to easily input relevant parameters and obtain shear strength predictions. The findings of this study are expected to promote the application of ML models in predicting the complex nonlinear behavior of UHPC structures, providing strong support for engineering practice.

Optimizing hydrogen evolution prediction: A unified approach using random forests, lightGBM, and Bagging Regressor ensemble model

Hydrogen, as a clean and versatile energy carrier, plays a pivotal role in addressing global energy challenges and transitioning towards sustainable energy systems. This study explores the convergence of machine learning (ML) for photocatalytic hydrogen evolution from sucrose solution using perovskite-type catalysts, namely LaFeO3 (LFO) and graphene-supported LaFeO3 (GLFO). This study pioneers the practical application of ML techniques, including Random Forests, LightGBM, and Bagging Regressor, to predict hydrogen yields in the presence of these photocatalysts. LFO and GLFO underwent a thorough characterization study to validate their successful preparation. Noteworthy, the highest hydrogen yield from the sucrose model solution was achieved using GLFO as 3.52 mmol/gcat. The optimum reaction conditions were experimentally found to be pH = 5.25, 0.15 g/L of catalyst amount, and 7.5 mM of HPC (hydrogen peroxide concentration). A pivotal contribution of this research lies in the practical application of ML models, culminating in the development of an ensemble model. This collaborative approach not only achieved an overall R2 of 0.92 but also demonstrated exceptional precision, as reflected in remarkably low error metrics. The mean squared logarithmic error (MSLE) was 0.0032, and the mean absolute error (MAE) was 0.049, underscoring the effectiveness of integrating diverse ML algorithms. This study advances both the understanding of photocatalytic hydrogen evolution and the practical implementation of ML in predicting intricate chemical reactions.

Real-Time Prediction of Petrophysical Properties Using Machine Learning Based on Drilling Parameters.

The prediction of rock porosity and permeability is crucial for assessing reservoir productivity and economic feasibility. However, traditional methods for obtaining these properties are time-consuming and expensive, making them impractical for comprehensive reservoir evaluation. This study introduces a novel approach to efficiently predict rock porosity and permeability for reservoir assessment by leveraging real-time machine learning models. Utilizing readily available drilling parameters, this approach offers a cost-effective alternative to traditional time-consuming methods to predict formation petrophysical parameters in real-time. The data set used in this study was collected from two vertical wells located in the Middle East. It encompasses drilling parameters such as the rate of penetration (ROP), gallons per minute (GPM), revolutions per minute (RPM), strokes per minute (SPP), torque, and weight on bit (WOB), along with the corresponding measurements of porosity (ϕ) and permeability (k) obtained through core analysis. Three machine learning models, namely, decision trees (DTs), random forest (RFs), and support vector machines (SVMs), were employed and evaluated for their effectiveness in predicting porosity and permeability. The results demonstrate promising performance across the different data sets. All three models achieved correlation coefficients (R) higher than 0.91 in predicting porosity. The RF model exhibited accurate predictions of permeability, achieving R values surpassing 0.92 in the various data sets. While the DT model displayed slightly lower performance, with the R-value decreasing to 0.88 in the testing data set, the SVM model suffered from overfitting, with R values dropping to 0.83 in the testing data set. The novelty of this work lies in the successful application of machine learning models to the real-time prediction of reservoir properties, providing a practical and efficient solution for the oil and gas industry. By achieving correlation coefficients exceeding 0.91 and showcasing the models' efficacy in a dynamic testing data set, this study paves the way for improved decision-making processes and enhanced exploration and production activities. The innovative aspect lies in the utilization of drilling parameters for timely and cost-effective estimation, transforming conventional reservoir evaluation methods.

Machine learning models in health prevention and promotion and labor productivity: A co-word analysis

Objective: The objective of this article is to carry out a co-word study on the application of machine learning models in health prevention and promotion, and its effect on labor productivity. Methodology: The analysis of the relevant literature on the proposed topic, identified in the last 15 years in Scopus, is considered. Articles, books, book chapters, editorials, conference papers and reviews refereed publications were considered. A thematic mapping analysis was performed using factor analysis and strategy diagrams to derive primary research approaches and identify frequent themes as well as thematic evolution. Results: The results of this study show the selection of 87 relevant publications with an average annual growth rate of 23.25% in related production. The main machine learning algorithms used, the main research approaches and key authors, derived from the analysis of thematic maps, were identified. Conclusions: This study emphasizes the importance of using co-word analysis to understand trends in research on the impact of health prevention and promotion on labor productivity. The potential benefits of using machine learning models to address this issue are highlighted and anticipated to guide future research focused on improvements in labor productivity through prevention and promotion of health. Originality: The identification of the relationship between work productivity and health prevention and promotion through machine learning models is a relevant topic but little analyzed in recent literature. The analysis of co-words allows us to establish the reference point of the state of the art in this regard and future trends.

Application of Machine Learning Models in Coaxial Bioreactors: Classification and Torque Prediction

Coaxial bioreactors are known for effectively dispersing gas inside non-Newtonian fluids. However, due to their design complexity, many aspects of their design and function, including the relationship between hydrodynamics and bioreactor efficiency, remain unexplored. Nowadays, various numerical models, such as computational fluid dynamics (CFD) and artificial intelligence models, provide exceptional opportunities to investigate the performance of coaxial bioreactors. For the first time, this study applied various machine learning models, both classifiers and regressors, to predict the torque generated by a coaxial bioreactor. In this regard, 500 CFD simulations at different aeration rates, central impeller speeds, anchor impeller speeds, and rotating modes were conducted. The results obtained from the CFD simulations were used to train and test the machine learning models. Careful feature scaling and k-fold cross-validation were performed to enhance all models’ performance and prevent overfitting. A key finding of the study was the importance of selecting the right features for the model. It turns out that just by knowing the speed of the central impeller and the torque generated by the coaxial bioreactor, the rotating mode can be labelled with perfect accuracy using k-nearest neighbors (kNN) or support vector machine models. Moreover, regression models, including multi-layer perceptron, kNN, and random forest, were examined to predict the torque of the coaxial impellers. The results showed that the random forest model outperformed all other models. Finally, the feature importance analysis indicated that the rotating mode was the most significant parameter in determining the torque value.

Credit Risk Assessment and Fraud Detection in Financial Transactions Using Machine Learning

Credit risk assessment and fraud detection are crucial tasks in the financial industry, vital to preserving financial organizations' legitimacy and sustainability. Traditional methods often fall short in accurately assessing risk and detecting fraudulent activities in a timely manner. In recent years, machine learning has emerged as a powerful tool for enhancing these processes, leveraging great dimensions of transactional statistics and superior algos for making more informed decisions. This research paper explores the usage of ML techniques in credit risk assessment and fraud detection within financial transactions.
 The paper begins with an overview of the importance of accurate risk assessment and fraud detection in financial transactions and introduces the role of machine learning in addressing these challenges. A comprehensive literature review is conducted to analyze existing methodologies, algorithms, and research trends in the field. Data acquisition and preprocessing techniques are discussed, emphasizing the importance of clean and relevant data for model training. Feature engineering strategies are explored to extract meaningful information from financial transaction data and enhance the predictive capabilities of machine learning models.
 Various machine learning algorithms suitable for credit risk assessment and fraud detection are examined, including LR, SVMs, RF, DTs and DNNs. The efficacy of these techniques is evaluated by discussing model metrics for assessment and ensemble approaches for boosting efficiency, with a focus on metrics such as accuracy, precision, recall, and ROC-AUC.
 The paper presents case studies and experimental results illustrating the application of machine learning models in real-world scenarios, highlighting their effectiveness in improving risk assessment and fraud detection processes. Additionally, difficulties such as imbalanced datasets, comprehensibility of the model and adherence to regulations are discussed, along with potential research directions and future trends in the field.
 In conclusion, this research emphasizes the transformative potential of machine learning in credit risk assessment and fraud detection within financial transactions. By leveraging advanced algorithms and data-driven approaches, financial institutions can enhance their decision-making processes, mitigate risks, and safeguard against fraudulent activities, ultimately contributing to a more secure and resilient financial ecosystem.

Fake Social Media Profile Detection and Reporting Using Machine Learning

Our research focuses on utilizing machine learning techniques, encompassing natural language processing and computer vision, to create an automated system for the detection and reporting of fake social media profiles across various platforms. Our approach involves feature extraction from both textual and visual content, followed by the application of machine learning models to classify profiles as fake or genuine. This system operates in real-time, monitoring user activity and promptly flagging suspicious profiles for user- initiated reporting. By combining the power of machine learning with cross-platform compatibility and user feedback, our solution aims to enhance online safety by swiftly identifying and addressing fraudulent social media profiles, thus fostering more secure and trustworthy online communities.

Application of machine learning models for green andsimultaneous determination of asiaticoside andmadecassoside in Centella asiatica

The artificial neuron network (ANN), which is a subfield of machine learning, has been widely applied in analytical chemistry for classification/pattern recognition, prediction, and modeling. ANN combined with UV spectrometry can be used to tackle the problem of overlapping spectra of a complicated matrix of herbal medicine. In the present study, ANN has been used for simultaneous determination of asiaticoside andmadecassoside in Centella asiatica collected from various provinces in Viet Nam based on UV spectra of standard reference and spiked samples. The absorption spectra of 108 C. asiatica samples were recorded in (190-250) nm of wavelength with an interval of 1 nm (61 variables) were used for data acquisition. An ANN model using traincgb function with 40 neural hidden layers was trained. The correlation coefficients were all higher than 0.9999. The concentration of asiaticoside and madecassoside in all tested samples revealed a good recovery, as compared to the referenced values. TheANN model can be considered as effective, time-saving and environment-friendly quantitative analysis tool for herbal medicine ® 2024 Journal of Science and Technology - NTTU

Application of machine learning models and landsat 8 data for estimating seasonal pm 2.5 concentrations.

Air pollution is a significant global challenge that affects many cities. In Europe, Bosnia and Herzegovina (BiH) are among the most highly polluted and are mainly affected by air pollution. In this study, we integrate open-source landsat 8 remote sensing products, topographical data, and the limited ground truth PM2.5 data to spatially predict the air quality level across different seasons in Tuzla Canton, BiH by adopting three pre-existing machine learning models, namely XGBoost, K-Nearest Neighbour (KNN) and Naive Bayes (NB). These classification models were implemented based on landsat 8 bands, environmental-derived indices, and topographical variables generated for the study area. Based on the predicted results, the XGBoost model exhibited the highest overall accuracy across all seasons. The predicted model results were used to generate spatial air quality maps. Based on the classification maps, the PM2.5 air quality level predicted for Tuzla Canton in the Winter Season is very unhealthy. The findings conclude that the PM2.5 air quality concentration in Tuzla Canton is relatively unsatisfactory and requires urgent intervention by the government to prevent further deterioration of air quality in Tuzla and other affected cantons in BiH.

Application of Machine Learning Modeling for the Upstream Oil and Gas Industry Injury Rate Prediction

Introduction: Yearly, the International Labor Organization report indicates many workplace accident occurrences. The degree of the happenings depends on the workplace environment setting and the incident regulatory measures implemented. By the nature of its work environment, the oil and gas upstream sector is susceptible to high incident rates. In the current fierce business competition and practices, improving productivity, quality, and other processes, such as Safety, is vital. Implementing well-designed safety procedures is the key to managing and reducing the risk level of workplace incidents. Methods: Recently, the application of Machine learning (ML) modeling for accident/injury prediction has been reported in the construction, mining, transport, and health sectors. Likewise, the objective of this paper was to implement three machine-learning-based models to predict injury rates in a drilling operation. The petroleum safety authority of Norway provided the datasets. First, the dataset was pre-processed, and then the selected features and target dataset were used for the modeling. Finally, the model prediction and performance accuracy analysis were performed. Results: Results showed that multivariable regression (MVR), Random Forest (RF), and Artificial Neural Network (ANN) machine learning algorithms-based models predict the test data with R2 values of 0.9576, 0.793, and 0.97036, respectively. Conclusion: As the common saying goes, 'prevention is better than cure.' For this, implementing methods such as improved work processes and Health, Safety, and Environment (HSE) mitigation procedures, workplace injuries, and accidents allow for reducing the risk level of workplace injuries. The application of integrated machine learning tools, along with carefully built-in workplace accident database implementation, will provide early detection and possible remedial precautions that can be taken to prevent workplace injuries/accidents/fatalities. However, extensive research and development are required to deploy the method in real life. Combining Machine Learning modeling and carefully designed safety measures is vital for successful and robust predictive tools.

Enhancing cryptocurrency market volatility forecasting with daily dynamic tuning strategy

This study proposes a novel parameter tuning strategy, daily dynamic tuning, and applies it to forecast volatility in the cryptocurrency market. Comparative analysis with HAR-RV and machine learning models based on fixed parameters demonstrates the superior predictive performance of the dynamic tuning-based model. These findings are corroborated in robustness tests. Using interpretable tools for machine learning model explanations, this study delves further into the driving factors behind the predictive performance of the dynamic tuning-based model. The results indicate that hash rate and the effective federal funds rate play significant roles among various forecasting factors. Further categorization of the forecasting factors reveals that blockchain indicators and macroeconomic indicators are more useful for predictions, while market indicators are relatively less informative. Moreover, a time-varying analysis of variable importance scores suggests a significant increase in the importance score of blockchain indicators from October 2022 onwards, coinciding with the EU passing landmark legislation on digital assets in October 2022. Finally, an economic value analysis indicates that the dynamic tuning-based model can achieve higher economic returns in practice compared to traditional fixed parameter models. These findings are significant for enhancing cryptocurrency market risk prediction and management and exploring the potential applications of machine learning models in volatility forecasting.