Prediction and interpretation of daily NFT and DeFi prices dynamics: Inspection through ensemble machine learning & XAI

Non Fungible Tokens (NFT) and Decentralized Finance (DeFi) assets have seen a growing media coverage and garnered considerable investor traction despite being classified as a niche in the digital financial sector. The lack of substantial research to demystify the dynamics of NFT and DeFi coins motivates the scrupulous analysis of the said sector. This work aims to critically delve into the evolutionary pattern of the NFTs and DeFis for performing predictive analytics of the same during the COVID-19 regime. The multivariate framework comprises the systematic inclusion of explanatory features embodying technical indicators, key macroeconomic indicators, and constructs linked to media hype and sentiment pertinent to the pandemic, nonlinear feature engineering, and ensemble machine learning. Isometric Mapping (ISOMAP) and Uniform Manifold Approximation and Projection (UMAP) techniques are conjugated with Gradient Boosting Regression (GBR) and Random Forest (RF) for enabling the predictive analysis. The predictive performance rationalizes the frameworks' capacity to accurately predict the prices of the majority of the NFT and DeFi coins during the ongoing financial distress period. Additionally, Explainable Artificial Intelligence (XAI) methodologies are used to comprehend the nature of the impact of the explanatory variables. Findings suggest that the daily movement of the NFTs and DeFi highly depends on their past historical movement. © 2023 The Authors

SCLAVOEM: hyper parameter optimization approach to predictive modelling of COVID-19 infodemic tweets using smote and classifier vote ensemble.

Fake COVID-19 tweets are dangerous since they are misinformative, completely inaccurate, as threatening the efforts for flattening the pandemic curve. Thus, aside the COVID-19 pandemic, dealing with fake news and myths about the virus constitute an infodemic issue, which must be tackled by ensuring only valid information. In this context, this study proposed the Synthetic Minority Over-Sampling Technique (SMOTE) and the classifier vote ensemble (SCLAVOEM) method as a fake news classifier and a hyper parameter optimization approach for predictive modelling of COVID-19 infodemic tweets. Hyper parameter optimization variables were deployed across specific points of the proposed model and a minority oversampling of training sets was applied within imbalanced class representations. Experimental applications by the SCLAVOEM for COVID-19 infodemic prediction returned 0.999 and 1.000 weighted averages for F-measure and area under curve (AUC), respectively. Thanks to the SMOTE, the performance increases of 3.74 and 1.11%; 5.05 and 0.29%; 4.59 and 8.05% was seen in three different data sets. Eventually, the SCLAVOEM provided a framework for predictive detecting 'fake tweets' and three classifiers: 'positive', 'negative' and 'click-trap' (piège à clics). It is thought that the model will automatically flag fake information on Twitter, hence protecting the public from inaccurate and information overload.

Predicting ozone formation in petrochemical industrialized Lanzhou city by interpretable ensemble machine learning.

Ground-level ozone (O3) formation depends on meteorology, precursor emissions, and atmospheric chemistry. Understanding the key drivers behind the O3 formation and developing an accurate and efficient method for timely assessing the O3-VOCs-NOx relationships applicable in different O3 pollution events are essential. Here, we developed a novel machine learning ensemble model coupled with a Shapley additive explanation algorithm to predict the O3 formation regime and derive O3 formation sensitivity curves. The algorithm was tested for O3 events during the COVID-19 lockdown, a sandstorm event, and a heavy O3 pollution episode (maximum hourly O3 concentration >200 µg/m3) from 2019 to 2021. We show that increasing O3 concentrations during the COVID-19 lockdown and the heavy O3 pollution event were mainly caused by the photochemistry subject to local air quality and meteorological conditions. Influenced by the sandstorm weather, low O3 levels were mainly attributable to weak sunlight and low precursor levels. O3 formation sensitivity curves demonstrate that O3 formation in the study area was in a VOCs-sensitive regime. The VOCs-specific O3 sensitivity curves can also help make hybrid and timely strategies for O3 abatement. The results demonstrate that machine learning driven by observational data has the potential to be a very useful tool in predicting and interpreting O3 formation.

Prediction and interpretation of daily NFT and DeFi prices dynamics: Inspection through ensemble machine learning & XAI

Non Fungible Tokens (NFT) and Decentralized Finance (DeFi) assets have seen a growing media coverage and garnered considerable investor traction despite being classified as a niche in the digital financial sector. The lack of substantial research to demystify the dynamics of NFT and DeFi coins motivates the scrupulous analysis of the said sector. This work aims to critically delve into the evolutionary pattern of the NFTs and DeFis for performing predictive analytics of the same during the COVID-19 regime. The multivariate framework comprises the systematic inclusion of explanatory features embodying technical indicators, key macroeconomic indicators, and constructs linked to media hype and sentiment pertinent to the pandemic, nonlinear feature engineering, and ensemble machine learning. Isometric Mapping (ISOMAP) and Uniform Manifold Approximation and Projection (UMAP) techniques are conjugated with Gradient Boosting Regression (GBR) and Random Forest (RF) for enabling the predictive analysis. The predictive performance rationalizes the frameworks' capacity to accurately predict the prices of the majority of the NFT and DeFi coins during the ongoing financial distress period. Additionally, Explainable Artificial Intelligence (XAI) methodologies are used to comprehend the nature of the impact of the explanatory variables. Findings suggest that the daily movement of the NFTs and DeFi highly depends on their past historical movement.

Bank Loan Default Prediction Using Ensemble Machine Learning Algorithm

Banks play an integral role in the financial system of any country which directly affects its economic status and growth. The major roles of banks include accepting deposits from its customers, using those deposits to lend money to the borrowers in return for some interest, granting credits, discounting on bills etc. But the main source of profit for the banks is the interest it receives from lending money to the borrowers. And in a scenario of global pandemic like Covid-19, the number of people requiring financial aid from the banks has increased drastically. But a major problem faced by these banks is the failure of timely loan repayment by the borrowers. So, to tackle this problem, banks now a days use some models to predict the possibility of loan repayment from the borrower. Factors like annual income, employment status, home ownership, current debt etc are taken into consideration to categorize the loan request as bad loan or not. So, this paper basically aims to develop a similar model, but using ensemble machine learning algorithm of Random Forest Classification. And perform a comparative analysis with the model (Decision Tree Classification) that are currently in use. After complete implementation of all the models it was concluded that Random Forest Classifier Outperformed Decision Tree Classifier in terms of accuracy. © 2022 IEEE.

GA-Stacking: A New Stacking-Based Ensemble Learning Method to Forecast the COVID-19 Outbreak

As a result of the increased number of COVID-19 cases, Ensemble Machine Learning (EML) would be an effective tool for combatting this pandemic outbreak. An ensemble of classifiers can improve the performance of single machine learning (ML) classifiers, especially stacking-based ensemble learning. Stacking utilizes heterogeneous-base learners trained in parallel and combines their predictions using a meta-model to determine the final prediction results. However, building an ensemble often causes the model performance to decrease due to the increasing number of learners that are not being properly selected. Therefore, the goal of this paper is to develop and evaluate a generic, data-independent predictive method using stacked-based ensemble learning (GA-Stacking) optimized by a Genetic Algorithm (GA) for outbreak prediction and health decision aided processes. GA-Stacking utilizes five well-known classifiers, including Decision Tree (DT), Random Forest (RF), RIGID regression, Least Absolute Shrinkage and Selection Operator (LASSO), and eXtreme Gradient Boosting (XGBoost), at its first level. It also introduces GA to identify comparisons to forecast the number, combination, and trust of these base classifiers based on the Mean Squared Error (MSE) as a fitness function. At the second level of the stacked ensemble model, a Linear Regression (LR) classifier is used to produce the final prediction. The performance of the model was evaluated using a publicly available dataset from the Center for Systems Science and Engineering, Johns Hopkins University, which consisted of 10,722 data samples. The experimental results indicated that the GA-Stacking model achieved outstanding performance with an overall accuracy of 99.99% for the three selected countries. Furthermore, the proposed model achieved good performance when compared with existing bagging-based approaches. The proposed model can be used to predict the pandemic outbreak correctly and may be applied as a generic data-independent model to predict the epidemic trend for other countries when comparing preventive and control measures. © 2023 Tech Science Press. All rights reserved.

Multilayer hybrid ensemble machine learning model for analysis of Covid-19 vaccine sentiments

This work presents the analysis of significant sentiments and attitudes of people towards the COVID-19 vaccination. The tweeter messages related to the COVID-19 vaccine is used for sentiment evaluation in this work. The proposed work consists of two steps: (i) natural processing language (NLP) and (ii) classification. The NLP is utilized for text pre-processing, tokenization, data labelling, and feature extraction. Further, a stack-based ensemble machine learning model is used to classify sentiments as positive, negative, or neutral. The stack ensemble machine learning model includes seven heterogeneous machine learning techniques namely, Naive Bayes, Logistic regression, Decision Tree, Random Forest, AdaBoost Classifier, Gradient Boosting, and extreme Gradient Boosting (XGB). The highest classification accuracy of 97.2%, 88.34%, 88.22%, 85.23%, 86.30%, 87.54%, 86.63%, and 88.78% is achieved by ensemble machine learning model, Logistic regression, AdaBoost, Decision Tree, Naive Bayes, Random Forest, Gradient Boosting, and XGB Classifier, respectively. [ FROM AUTHOR] Copyright of Journal of Intelligent & Fuzzy Systems is the property of IOS Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

DEVELOPMENT OF ENSEMBLE MACHINE LEARNING MODEL TO IMPROVE COVID-19 OUTBREAK FORECASTING

The world is currently facing the coronavirus disease 2019 (COVID-19 pandemic). Forecasting the progression of that pandemic is integral to planning the necessary next steps by governments and organizations. Recent studies have examined the factors that may impact COVID-19 forecasting and others have built models for predicting the numbers of active cases, recovered cases and deaths. The aim of this study was to improve the forecasting predictions by developing an ensemble machine-learning model that can be utilized in addition to the Naïve Bayes classifier, which is one of the simplest and fastest probabilistic classifiers. The first ensemble model combined gradient boosting and random forest classifiers and the second combined support vector machine and random-forest classifiers. The numbers of confirmed, recovered and death cases will be predicted for a period of 10 days. The results will be compared to the findings of previous studies. The results showed that the ensemble algorithm that combined gradient boosting and random-forest classifiers achieved the best performance, with 99% accuracy in all cases. © 2022, Scientific Research Support Fund of Jordan. All rights reserved.

Machine Learning Technique with Spider Monkey Optimization for COVID-19 Sentiment Analysis

The coronavirus (COVID-19) has unquestionably posed one of the most difficult problems in human history. As of May 5, 2021, the global death toll from the on going COVID-19 epidemic was at 150 million. Monitoring, managing, and finally eradicating the disease can be made easier by understanding the mood represented in people's social media remarks. It is the goal of this research to educate social media policy, such as how much reasonableness is required to curb misrepresentation on social media. This research also examines people's opinions on COVID-19 over social media sharing and interaction on Twitter. For our studies, we've generated a new large-scale sentiment data collection called COVIDSENTI that includes 90,000 tweets about the COVID-19 epidemic from February to March of the following year. We classified the tweets based on their emotional tone: good, negative, or neutral. In this work, ensemble machine learning classifier and uses the Spider Monkey optimization (SMO) for selecting the optimal features. The raw datasets are cleaned by using pre-processing techniques and important features are extracted by using feature extraction practises. We used multiple parameter measurements to assess the gathered tweets for sentiment categorization. © 2022 IEEE.

Using Machine Learning Techniques to Explore the Possibilities of Reducing the Spread of Corona Virus and its New Variants

The Corona pandemic has been around for a while, and its threat to the world is growing. We believe that climate parameters and health prevention measures could be related to the number of reported Corona daily cases. In the literature there were different views on the nature of these relations using several datasets recorded from various parts of the world. In our research, data collected from zones with concentrated Corona cases: China, Europe and the United States were analyzed to understand the relation with climate as well as data at the global level to understand the relation with health prevention measures. Feature importance analysis revealed that temperature is the most important contributing attribute to the Corona cases' prediction models, followed by relative humidity. As well, the percentage of mask use and percentage of fully vaccinated individuals were found to have a great influence on the number of new Corona daily cases. The designed machine learning ensemble techniques had a maximum predication accuracy of 89.08%, and the produced possible interpretations for the designed models agreed with the performed feature importance analyses. We believe that the analysis approach followed in this research as well as the achieved findings could be very useful to other researchers who are interested in conducting more research investigation in the same research area on the new Corona variants. We also believe that policy makers could consider the findings of our research as they effectively plan their future health precautions measures to avoid further spread of the virus. © 2022 IEEE.

Sentimental Analysis of COVID-19 Related Messages in Social Networks by Involving an N-Gram Stacked Autoencoder Integrated in an Ensemble Learning Scheme.

The current population worldwide extensively uses social media to share thoughts, societal issues, and personal concerns. Social media can be viewed as an intelligent platform that can be augmented with a capability to analyze and predict various issues such as business needs, environmental needs, election trends (polls), governmental needs, etc. This has motivated us to initiate a comprehensive search of the COVID-19 pandemic-related views and opinions amongst the population on Twitter. The basic training data have been collected from Twitter posts. On this basis, we have developed research involving ensemble deep learning techniques to reach a better prediction of the future evolutions of views in Twitter when compared to previous works that do the same. First, feature extraction is performed through an N-gram stacked autoencoder supervised learning algorithm. The extracted features are then involved in a classification and prediction involving an ensemble fusion scheme of selected machine learning techniques such as decision tree (DT), support vector machine (SVM), random forest (RF), and K-nearest neighbour (KNN). all individual results are combined/fused for a better prediction by using both mean and mode techniques. Our proposed scheme of an N-gram stacked encoder integrated in an ensemble machine learning scheme outperforms all the other existing competing techniques such unigram autoencoder, bigram autoencoder, etc. Our experimental results have been obtained from a comprehensive evaluation involving a dataset extracted from open-source data available from Twitter that were filtered by using the keywords "covid", "covid19", "coronavirus", "covid-19", "sarscov2", and "covid_19".