Browsing by Author "Smail, Linda"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Bitcoin price forecasting: Linear discriminant analysis with sentiment evaluation(Association for Computing Machinery, 2021-08-25) Gurrib, Ikhlaas; Kamalov, Firuz; Smail, LindaCryptocurrencies such as bitcoin have garnered a lot of attention in recent months due to their meteoric rise. In this paper, we propose a new method for predicting the direction of bitcoin price using linear discriminant analysis (LDA) together with sentiment analysis. Concretely, we train an LDA-based classifier that uses the current bitcoin price information and Twitter headline news in order to forecast the next-day direction of bitcoin price. The proposed model achieves highly accurate results beating several benchmark targets. In particular, the proposed approach produces forecast accuracy of 0.828 and AUC of 0.840 on the test data. © 2021 Association for Computing Machinery. All rights reserved.Item Enough of the chit-chat: A comparative analysis of four AI chatbots for calculus and statistics(Kaplan Singapore, 2023-06-29) Calonge, David Santandreu; Smail, Linda; Kamalov, FiruzThis article presents a comparative analysis of four AI chatbots with potential utilization in the fields of mathematics education and statistics, namely ChatGPT, GPT-4, Bard, and LLaMA. Our objective is to evaluate and compare the features, functionalities, and potential applications of these platforms within the domains of calculus and statistics. By examining their strengths and limitations, this study aims to provide insights into the selection and implementation of AI chatbots in calculus and statistics to enhance student learning. The results of the comparative analysis reveal that, while not perfect, GPT-4 outperforms ChatGPT, Bard, and LLaMA as a learning tool in calculus and statistics. Findings also reveal that chatbots may have a positive transformational impact on higher education. © 2023 David Santandreu Calonge, Linda Smail and Firuz Kamalov..Item Forecasting with Deep Learning: S&P 500 index(Institute of Electrical and Electronics Engineers Inc., 2020-12) Kamalov, Firuz; Smail, Linda; Gurrib, IkhlaasStock price prediction has been the focus of a large amount of research but an acceptable solution has so far escaped academics. Recent advances in deep learning have motivated researchers to apply neural networks to stock prediction. In this paper, we propose a convolution-based neural network model for predicting the future value of the S&P 500 index. The proposed model is capable of predicting the next-day direction of the index based on the previous values of the index. Experiments show that our model outperforms a number of benchmarks achieving an accuracy rate of over 55%. ©2020 IEEEItem Modelling Entrepreneurial Intentions and Attitudes towards Business Creation among Emirati Students Using Bayesian Networks(World Association for Sustainable Development, 2022) Smail, Linda; Alawad, Mouawiya; Abaza, Wasseem; Kamalov, Firuz; Alawadhi, HamdahPURPOSE: Entrepreneurial intentions (EI) have been a major focus of research studied using generic models. This paper will use Bayesian Networks (BN) to model entrepreneurial intentions as they provide an advantage over classical methods. METHODOLOGY: A cross-sectional study was conducted among a random sample of 324 Emirati University students by implementing the Unsupervised Structural Learning algorithm to build the model. FINDINGS: Entrepreneurial intentions are highly affected by attitude, self-efficacy, subjective norms, and opportunity feasibility, while obstacles and university opportunity feasibility are the variables whose influence on entrepreneurial intention is less. ORIGINALITY: This study looked at entrepreneurship intention and attitudes among students who are not yet entrepreneurs using Bayesian Networks as a new technique to discover how this can affect students’ intention in starting a business. Conclusions stem from the existing Emirati social construct (people-centric society of the Arab world, rather than system-centric society of the Western world). This has created value-added contributions of the paper to the research questions. © 2022 by all the authors of the article above.Item Stock price forecast with deep learning(Institute of Electrical and Electronics Engineers Inc., 2020-11-08) Kamalov, Firuz; Smail, Linda; Gurrib, IkhlaasIn this paper, we compare various approaches to stock price prediction using neural networks. We analyze the performance fully connected, convolutional, and recurrent architectures in predicting the next day value of SP 500 index based on its previous values. We further expand our analysis by including three different optimization techniques: Stochastic Gradient Descent, Root Mean Square Propagation, and Adaptive Moment Estimation. The numerical experiments reveal that a single layer recurrent neural network with RMSprop optimizer produces optimal results with validation and test Mean Absolute Error of 0.0150 and 0.0148 respectively. © 2020 IEEE.