Bikramaditya Ghosh

Accurately forecasting stock fluctuations can yield high investment returns while minimizing risk. However, market volatility makes these projections unlikely. As a result, stock market data analysis is significant for research. Analysts and researchers have developed various stock price prediction systems to help investors make informed judgments. Extensive studies show that machine learning can anticipate markets by examining stock data. This article proposed and evaluated different ensemble learning techniques such as max voting, bagging, boosting, and stacking to forecast the Nifty50 index efficiently. In addition, an embedded feature selection is performed to choose an optimal set of fundamental indicators as input to the model, and extensive hyperparameter tuning is applied using grid search to each base regressor to enhance performance. Our findings suggest the bagging and stacking ensemble models with random forest (RF) feature selection offer lower error rates. The bagging and stacking regressor model 2 outperformed all other models with the lowest root mean square error (RMSE) of 0.0084 and 0.0085, respectively, showing a better fit of ensemble regressors. Finally, the findings show that machine learning algorithms can help fundamental analyses make stock investment decisions.

Purpose: The authors target the interrelationships between non-fungible tokens (NFTs), decentralized finance (DeFi) and carbon allowances (CA) markets during 2021–2023. The recent shift of crypto and DeFi miners from China (the People's Republic of China, PRC) green hydro energy to dirty fuel energies elsewhere induces investments in carbon offsetting instruments; this is a backdrop to the authors’ investigation.Design/methodology/approach: The quantile vector autoregression (VAR) approach is employed to examine extreme-quantile-connectedness and spillovers among the NFT Index (NFTI), DeFi Pulse Index (DPI), KraneShares Global Carbon Strategy ETF price (KRBN) and the Solactive Carbon Emission Allowances Rolling Futures Total Return Index (SOLCARBT).Findings: At bull markets, DPI is the only consistent net shock transmitter as NFTI transmits innovations only at the most extreme quantile. At bear markets, KRBN and SOLCARBT are net shock transmitters, while NFTI is the only consistent net shock receiver. The receiver-transmitter roles change as a function of the market conditions. The increases in the relative tail dependence correspond to the stress events, which make systemic connectedness augment, turning market-specific idiosyncratic considerations less relevant.Originality/value: The shift of digital asset miners from the PRC has resulted in excessive fuel energy consumption and aggravated environmental consequences regarding NFTs and DeFi mining. Although there exist numerous studies dedicated to CA trading and its role in carbon print reduction, the direct nexus between NFT, DeFi and CA has never been addressed in the literature. The originality of the authors’ research consists in bridging this void. Results are valuable for portfolio managers in bull and bear markets, as the authors show that connectedness is more intense under such conditions.

Predicting equities market trends is one of the most challenging tasks for market participants. This study aims to apply machine learning algorithms to aid in accurate Nifty 50 index trend predictions. The paper compares and contrasts four forecasting methods: artificial neural networks (ANN), support vector machines (SVM), naive bayes (NB), and random forest (RF). In this study, the eight technical indicators are used, and then the deterministic trend layer is used to translate the indications into trend signals. The principal component analysis (PCA) method is then applied to this deterministic trend signal. This study's main influence is using the PCA technique to find the essential components from multiple technical indicators affecting stock prices to reduce data dimensionality and improve model performance. As a result, a PCA-machine learning (ML) hybrid forecasting model was proposed. The experimental findings suggest that the technical factors are signified as trend signals and that the PCA approach combined with ML models outperforms the comparative models in prediction performance. Utilizing the first three principal components (percentage of explained variance=80%), experiments on the Nifty 50 index show that support vector classifer (SVC) with radial basis function (RBF) kernel achieves good accuracy of (0.9968) and F1-score (0.9969), and the RF model achieves an accuracy of (0.9969) and F1-Score (0.9968). In area under the curve (AUC) performance, SVC (RBF and Linear kernels) and RF have AUC scores of 1.

We investigate the connectedness of automated market makers (AMM) that play a pivotal role in liquidity and ease of operations in the decentralized exchange (DEX). By applying the TVP-VAR model, our findings show higher level of connectivity during periods of turmoil (such as Delta, Omicron variants of SARS-Covid, and the Russia Ukraine conflict). Furthermore, risk transmission/reception is found to be independent of the platform on which they typically run (Ethereum based AMMs were both emitters as well as receivers). Pancake (a Binance based AMM) and Perpetual Protocol (Ethereum based AMM) emerged as moderate to high receivers of risk transmission, whereas all of the other AMMs, including Ethereum, were found to be risk emitters at varying degrees. We argue that AMMs typically depend on the underlying smart contracts. If the contract is flexible, AMMs can vary (either receiver or emitter), otherwise AMMs behave in tandem.