The recent high performance of ChatGPT on several standardized academic tests has thrust the topic of artificial intelligence (AI) into the mainstream conversation about the future of education. As deep learning is poised to shift the teaching paradigm, it is essential to have a clear understanding of its effects on the current education system to ensure sustainable development and deployment of AI-driven technologies at schools and universities. This research aims to investigate the potential impact of AI on education through review and analysis of the existing literature across three major axes: applications, advantages, and challenges. Our review focuses on the use of artificial intelligence in collaborative teacher–student learning, intelligent tutoring systems, automated assessment, and personalized learning. We also report on the potential negative aspects, ethical issues, and possible future routes for AI implementation in education. Ultimately, we find that the only way forward is to embrace the new technology, while implementing guardrails to prevent its abuse.
Forecasting directional movement of stock price using machine learning tools has attracted a considerable amount of research. Two of the most common input features in a directional forecasting model are stock price and return. The choice between the former and the latter variables is often subjective. In this study, we compare the effectiveness of stock price and return as input features in directional forecasting models. We perform an extensive comparison of the two input features using 10-year historical data of ten large cap US companies. We employ four popular classification algorithms as the basis of the forecasting models used in our study. The results show that stock price is a more effective standalone input feature than return. The effectiveness of stock price and return equalize when we add technical indicators to the input feature set. We conclude that price is generally a more potent input feature than return value in predicting the direction of price movement. Our results should aid researchers and practitioners interested in applying machine learning models to stock price forecasting.
Purpose The purpose of this paper is to shed fresh light into whether an energy commodity price index (ENFX) and energy blockchain-based crypto price index (ENCX) can be used to predict movements in the energy commodity and energy crypto market. Design/methodology/approach Using principal component analysis over daily data of crude oil, heating oil, natural gas and energy based cryptos, the ENFX and ENCX indices are constructed, where ENFX (ENCX) represents 94% (88%) of variability in energy commodity (energy crypto) prices. Findings Natural gas price movements were better explained by ENCX, and shared positive (negative) correlations with cryptos (crude oil and heating oil). Using a vector autoregressive model (VAR), while the 1-day lagged ENCX (ENFX) was significant in estimating current ENCX (ENFX) values, only lagged ENCX was significant in estimating current ENFX. Granger causality tests confirmed the two markets do not granger cause each other. One standard deviation shock in ENFX had a negative effect on ENCX. Weak forecasting results of the VAR model, support the two markets are not robust forecasters of each other. Robustness wise, the VAR model ranked lower than an autoregressive model, but higher than a random walk model. Research limitations/implications Significant structural breaks at distinct dates in the two markets reinforce that the two markets do not help to predict each other. The findings are limited by the existence of bubbles (December 2017-January 2018) which were witnessed in energy blockchain-based crypto markets and natural gas, but not in crude oil and heating oil. Originality/value As per the authors’ knowledge, this is the first paper to analyze the relationship between leading energy commodities and energy blockchain-based crypto markets.
Purpose Cryptocurrencies such as Bitcoin (BTC) attracted a lot of attention in recent months due to their unprecedented price fluctuations. This paper aims to propose a new method for predicting the direction of BTC price using linear discriminant analysis (LDA) together with sentiment analysis. Design/methodology/approach Concretely, the authors train an LDA-based classifier that uses the current BTC price information and BTC news announcements headlines to forecast the next-day direction of BTC prices. The authors compare the results with a Support Vector Machine (SVM) model and random guess approach. The use of BTC price information and news announcements related to crypto enables us to value the importance of these different sources and types of information. Findings Relative to the LDA results, the SVM model was more accurate in predicting BTC next day’s price movement. All models yielded better forecasts of an increase in tomorrow’s BTC price compared to forecasting a decrease in the crypto price. The inclusion of news sentiment resulted in the highest forecast accuracy of 0.585 on the test data, which is superior to a random guess. The LDA (SVM) model with asset specific (news sentiment and asset specific) input features ranked first within their respective model classifiers, suggesting both BTC news sentiment and asset specific are prized factors in predicting tomorrow’s price direction. Originality/value To the best of the authors’ knowledge, this is the first study to analyze the potential effect of crypto-related sentiment and BTC specific news on BTC’s price using LDA and sentiment analysis.
This study analyses whether returns of top market capitalised cryptocurrencies are affected by their movements or major global macroeconomic news. Daily data are collected for the leading 10 cryptocurrencies from July 2017-December 2018. This study, (i) tests whether lagged variables can help predict other variables' returns through a vector autoregression (VAR) model, (ii) analyses the response of cryptocurrencies to one standard deviation shock on Bitcoin's returns, and (iii) decomposes factors that contribute to variance and tests for structural breaks. Findings show that most cryptocurrencies do not significantly affect other variances, except for Monero, which represented between 19% and 45% of the variances of five cryptocurrencies. Autoregressive (AR) models are superior in forecasting one day ahead return forecasts, compared to the VAR model, whereas the random walk (RW) model ranked last. Although remarkable structural breaks are observed via impulse response functions during December 2017-January 2018, no major news announcements were released on the same day the breaks occurred. Overall, this study suggests the need for high-frequency cryptocurrency prices to tackle the issue of the relationship between intraday news release and cryptocurrencies.
The aim of this study is to investigate if Ichimoku Cloud can serve as a technical analysis indicator to improve stock price prediction for leading US energy companies. The methodology centers on the application of the Ichimoku Cloud as a trading system. The daily stock prices of the top ten constituents of the S&P Composite 1500 Energy Index -spanning the period from 12 th April, 2012 to 31 st July, 2019 -were sourced for experimentation. The performance of the Ichimoku Cloud is measured using both the Sharpe and Sortino ratios to adjust for total and downside risks. The analysis is split into pre and post oil crisis to account for the drop in energy stock prices during the July 2014 -December 2015. The model is also benchmarked against the naïve buy-and-hold strategy. The capacity of the Ichimoku indicator to provide signals during strengthening trends is analyzed. Despite the drop in energy stock prices, number of trades continued to increase along with profit opportunities. The PSX stock ranked first, with the highest Sharpe ratio, Sortino ratio, and Sharpe per number of trade. As expected, a number of buying signals occurred during strengthening bullish periods. Surprisingly, various sell signals also occurred during similar strengthening bullish trends. Most of the buy and sell signals under the Ichimoku indicator occurred outside of strengthening of bullish or bearish trends. The overall findings suggest that speculators can benefit from the use of the Ichimoku Cloud in analyzing energy stock price movements. In addition, it has the potential to reduce susceptibility to changes in energy prices. Last, the strength of the trend in place needs to be captured as it served as an additional layer of information which can improve the decision making process of the trader.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.