3830 research outputs found
Sort by
Perform the Stock Prediction Using the Sentiment Analysis and Time Series Forecasting Approaches to Determine the Optimal One
No full textStock returns are affected by a variety of factors, among which the social media remarks of public figures are one of the more important aspects on the stock market trend. On top of that, latest news about the product of the stock also matters. In this paper, we determine the sentiment type of public figures' social media remarks from the perspective of textual sentiment, and compare them with the stock chart of the day to analyse the connection between the two. Specifically, we first construct a dataset of public figures' social remarks and classify the sentiment types, and then we use the network model BERT for training to be able to judge the sentiment type of a new remark when it is inputted, which serves as a basis for stock prediction. The experiment shows that the public figure's speech and the news will have a strong impact on the stock trading on the same day, but the impact is small for a long time, at the same time, the more influential the public figure is, the more obvious the impact on the stock. The development and wealth of countries depend heavily on the stock market. Data mining and artificial intelligence methods are required to analyse stock market data. The financial success of particular businesses is one of the important factors that has a significant impact on stock price volatility. However, news reports also have a significant impact on how the stock market moves. In this research, we use sentiment classification to use non-measurable data, such as financial news articles, to forecast a company's future stock trend. We seek to cast light on the effect of news reports on the stock market by analysing the connection between news and stock movement. Our study seeks to advance knowledge of the function of news sentiment in forecasting stock market trends. The dataset used in this study consists of news headlines from the financial news website, Financial Times, and the prediction task is to classify the direction of the stock price changes as either positive or negative. The purpose of this study is to evaluate the effectiveness of sentiment analysis for stock prediction and to compare the performance of different algorithms
A study on assessing the integration of Artificial Intelligence (AI) on risk management practices within the Information Technology industry in India
No full textThe study investigates risk management practices within the Information Technology (IT) industry in India, focusing on the roles of AI adoption, organizational culture, technological infrastructure, and regulatory compliance. Through rigorous analysis including reliability testing, demographic examination, descriptive statistics, correlation analysis, and multiple regression modeling, the research uncovers insights into the complex dynamics of risk management in the Indian IT sector. Key findings reveal the transformative impact of AI adoption on risk management effectiveness. Organizations investing in AI-powered solutions demonstrate higher levels of risk management efficacy, aligning with global trends in AI adoption for business optimization and resilience. Additionally, organizational culture emerges as a crucial determinant of risk management outcomes, with cultures fostering innovation, collaboration, and risk-awareness exhibiting more robust practices.
Moreover, the study highlights the pivotal role of technological infrastructure in shaping risk management practices. Organizations with robust, flexible, and compatible infrastructures are better equipped to implement and sustain effective strategies. Regulatory compliance also emerges as a significant driver, with adherence to data privacy regulations positively influencing risk management effectiveness. Based on these findings, recommendations are provided to enhance risk management practices within the Indian IT industry. These include increasing investment in AI-related initiatives, fostering innovation and collaboration, prioritizing investments in data security and governance, and staying abreast of regulatory changes. Additionally, suggestions for further research are outlined, such as longitudinal studies on the effects of AI adoption and comparative analyses across different industry sectors and regions. As a conclusion, the study offers valuable insights for stakeholders in the Indian IT industry to inform strategic decision-making processes and initiatives aimed at strengthening risk management capabilities, organizational resilience, and regulatory compliance
Role of artificial intelligence in optimizing automotive supply chain planning and decision making
No full textThe automotive industry operates within a complex and dynamic global supply chain ecosystem, where efficient planning and decision-making are paramount to ensure competitiveness and sustainability. This dissertation embarks on a comprehensive investigation into the role of artificial intelligence (AI) in optimizing automotive supply chain planning and decision-making processes, with a particular focus on integrating insights from random sampling strategy and quantitative data analysis techniques.
Challenges in the Automotive Industry: The dissertation initiates by delving into the current state of the automotive industry and elucidates the key challenges confronted by supply chain stakeholders. These challenges include demand volatility, supply chain disruptions, and escalating customer expectations, all of which underscore the necessity for innovative approaches to supply chain management.
Exploration of AI Technologies: Building upon this foundation, the study navigates through various AI technologies such as machine learning, predictive analytics, and optimization algorithms, probing their potential applications in mitigating the challenges. By leveraging these advanced technologies, automotive companies can bolster their capacity to forecast demand accurately, optimize inventory levels, enhance supplier management, streamline production scheduling, optimize transportation logistics, manage risks, and advance sustainability initiatives within their supply chains. Furthermore, the integration of insights from random sampling strategies ensures a rigorous approach to data collection and representation, thereby enhancing the robustness and validity of the research findings.
Analysis of AI Applications: A critical analysis of AI applications within the automotive supply chain domain is meticulously presented, highlighting the multifaceted roles AI can play across various operational domains. From demand forecasting to sustainability initiatives, each aspect is scrutinized to delineate the potential benefits and challenges associated with AI adoption. Through empirical evidence, case studies, and theoretical frameworks, the dissertation paints a comprehensive picture of how AI can revolutionize automotive supply chain management practices.
Implications and Considerations: Moreover, the dissertation delves into the implications of AI adoption on organizational structures, workforce skills, and ethical considerations within the automotive industry. As AI permeates various aspects of supply chain operations, organizational structures may evolve, necessitating shifts in workforce skillsets and competencies. Additionally, ethical considerations surrounding AI implementation, such as data privacy, algorithmic bias, and transparency, are scrutinized to ensure responsible and ethical deployment of AI technologies in the automotive supply chain context.
In conclusion, this dissertation contributes significantly to the burgeoning body of knowledge on AI-enabled supply chain optimization in the automotive industry. By synthesizing insights from diverse sources and methodologies, the study provides practical recommendations for policymakers, industry practitioners, and academics alike. By embracing AI technologies strategically, automotive companies can augment efficiency, agility, and resilience in their supply chain operations, thereby driving sustainable growth and competitive advantage in an increasingly digitalized and interconnected world
Can Retaining Older Workers in the Workplace Benefit Organisations in South Africa?
No full textThe aim of the study was to explore whether retaining older workers in the workplace could benefit organisations in South Africa, against the backdrop of increasing numbers of people around the world being forced to work longer, or return to the workforce after retirement. This was due to socio-economic factors, which were currently being further exacerbated by the global inflationary impact on pensions and savings. Apprehension about losing meaning and purpose in life after retirement were further factors that emerged during the research for this dissertation. The objectives were thus to explore the transitioning of older, senior employees in an organisation to a coaching and mentoring role to potentially help mitigate the serous skills shortage in South Africa. Data collection took the form of seven semi-structured, online interviews with the identified participants in South Africa. The data was analysed using an inductive thematic analysis to describe and interpret the information. The interviewees confirmed that older members of the workforce proved to be a rich source of talent and experience for the organisations that engage them and have, in many instances, become catalysts for change and intergenerational diversity in the workplace. Despite the positive potential of retaining more mature members of the workforce, however, the reality of the current socio-economic situation in South Africa, proved to be far more complex than was anticipated at the outset of the study. To this end, the objectives of this study had to be revisited and some harsh truths had to be acknowledged. Thus, it was found that transitioning more mature members of the workforce to a coaching and mentoring role would require a significant mindset shift and more structured human resource management guidelines and processes to facilitate it
Optimizing logistics routes with advanced algorithms: comprehensive route prediction and efficiency enhancement
No full textThis study leverages machine learning and data mining techniques to optimise logistics transportation routes, aiming to enhance efficiency in short-distance deliveries. The research aims to develop reliable predictive models, providing optimization solutions for shortdistance logistics routes by comparing the effectiveness of traditional machine learning algorithms and deep neural networks. The model training used historical data from Amazon Logistics in 2018, with key features including route efficiency, package density, and transit time. The study follows the CRISP-DM framework, evaluating the performance of different models in route prediction and optimization. The deep neural network model, combined with graph theory-based algorithms such as the Traveling Salesman Problem (TSP), significantly improves route optimization outcomes. The research concludes that integrating advanced deep learning models with traditional optimization techniques can lead to substantial cost savings and efficiency improvements for logistics companies, while also enhancing customer satisfaction. Future research is recommended to explore larger datasets, real-time data integration, and the impact of economic and social factors
Utilizing Transformer Models and Graph Neural Networks for Timestamp-Based Cryptocurrency Price Prediction: A Deep Learning Approach
Get PDFThis study delves into the realm of cryptocurrency price prediction using cutting-edge deep learning techniques, specifically Transformer models and Graph Neural Networks (GNN). We conduct a comprehensive evaluation, benchmarking these methods against traditional models like ARIMA, Simple RNN, and Prophet on Ethereum (ETH) and Bitcoin (BTC) closing prices. Notably, the Transformer model showcases remarkable accuracy in BTC_close predictions, boasting an RMSE of 0.02395 and MAE of 0.02312, surpassing the performance of ARIMA. Conversely, GNN emerges as the top performer for ETH_close, delivering an impressive RMSE of 1111.39 and MAE of 1055.11. Despite its computational simplicity, Simple RNN falls short in comparison. This research contributes valuable insights into harnessing state-of-the-art deep learning architectures for accurate cryptocurrency price forecasting, highlighting the efficacy of Transformer models and GNNs in capturing intricate temporal dependencies within the dynamic cryptocurrency market landscape
Malware Profiling and Classification using machine learning algorithms
No full textThe study done on "Malware Profiling and Classification using Machine Learning Algorithms" compares multiple machine learning models for malware detection and profiling to enhance cybersecurity. Machine learning adaptable skills were used to identify and classify complex malware threats with the help of algorithms like SVM, Random Forest, and Autoencoders to analyze historical malware data. These models were selected for their pattern recognition and anomaly detection successes in large datasets. The data was carefully preprocessed to assure accuracy and relevance and machine learning algorithms were taught to recognize complex malware patterns. Each model was rigorously evaluated using 70% training and 30% validation data throughout the inquiry. The models' performance was assessed using accuracy, precision, recall, F1 score, AUC, and ROC curve. The SVM model gives proper results identifying safe and dangerous software with 0.99 AUC. However, the Random Forest and Autoencoder models scored 1.0 in the AUC statistic which is ideal. These results showed that these models had nearly minimal false positives, which is crucial in malware detection systems.
A near-perfect score of 0.9999 showed that the Random Forest model accurately classified data points with 1.0 accuracy suggests that the model predicted no false positives. The model recognized almost all real malware occurrences with a recall score of 0.9998 indicating success. The model's balanced prediction abilities were confirmed by its 0.9999 F1 score whereas the Autoencoder model had an accuracy of 0.9959, a precision of 0.9955, and an F1 score that matched the Random Forest. The recall rate of 0.9962 indicated that it was somewhat better at detecting true positives than the Random Forest model. This model's AUC score was 1.0, and its ROC performance was crucial for confidently differentiating classes. A ROC curve comparison showed that Random Forest and Autoencoder models performed better. The ROC curve shows how efficiently binary classifier systems identify malware as when the curve closely matches the left-hand and top ROC space boundaries, the model is more accurate. Both models have excellent classifier behavior as seen by the ROC curve in the top left corner. All models examined were effective, however the Autoencoder model was somewhat better, making it the preferred malware classification and profiling technique
Examining the Transformation of IT Departments Post-adoption of Cloud Computing Services
Get PDFThe aim of this research is to explore and understand the evolving roles and functions of IT departments within organizations following the adoption of cloud computing services. Hence the study examines the factors that drive organizations to adopt cloud computing services, further the study analyses the impact of cloud computing adoption on traditional IT department functions. In addition to this, the study identifies the new roles and responsibilities that emerge within IT departments post-cloud adoption. Later, the study assesses the challenges and opportunities presented by the transformation of IT departments and finally, the study provides recommendations for organizations on effectively managing the transition of IT roles in the cloud era. The target population for this research contains 80 IT department professionals who aware of cloud computing services. The gathering of survey data is essential to studying how IT departments have changed since utilizing cloud computing services. The survey instrument was created on the basis of thorough literature review that incorporates validated scales. The survey has gathered quantitative data and it was examined with the help of statistical tools like SPSS 25. Descriptive statistics was implemented in order to analyse the recognize trends. The evolution of IT departments inside the wake of cloud computing adoption indicates a fundamental transformation in roles, features, and organizational strategies. Through this complete look at and by way of drawing upon previous research, it will become obtrusive that cloud adoption has catalysed a paradigm shift, riding IT departments to transition from conventional infrastructure management to strategic enablers of innovation and performance
The spotlight effect: the role of social anxiety, locus of control, age and self-esteem
No full textThis study investigated the spotlight effect using self-focused information to predict how others perceive us while examining the influence of social anxiety, self-esteem, LOC, age, and gender. The study involved 129 participants (M=37, F=92), ages ranging from 18-75 (M=38.95, SD=11.44). The survey included sociodemographic and psychological scale questionnaires such as INCOM, LSAS-SR, Levenson’s LOC and RSE. The t-test indicated no significant difference in the spotlight effect based on gender, while Spearman’s rho indicated a negative relationship with age and a positive relationship with self-esteem and internal LOC. ANOVA indicated no interaction between age and gender and linear regression found the spotlight effect predicted social anxiety. Multiple regression indicated external LOC (chance), social anxiety and age were combined predictors of the spotlight effect, age being strongest. Results align somewhat with previous research but require further investigation into comparison directions. LOC needs further investigation due to the lack of previous research
The impact of dysmenorrhea on burnout & quality of life in Ireland
No full textThis study aims to understand the relationship between dysmenorrhea, occupational burnout and health-related quality of life (HRQL) of people who menstruate in Ireland, and whether the type of dysmenorrhea impacts HRQL. A quantitative correlational and cross-sectional analysis was carried out. 82 participants (M=32.13) completed an online questionnaire relating to severity of dysmenorrhea, burnout and six aspects of HRQL. Regression analysis found that dysmenorrhea did not predict burnout (P =.232), however severity of dysmenorrhea does predict worse physical, social, and psychological aspects of HRQL (P<.001). An independent samples t – test found that secondary dysmenorrhea leads to poorer HRQL then primary dysmenorrhea (P<.001). Longitudinal and qualitative research is needed to understand the psychological impacts of the menstrual cycle and secondary dysmenorrhea. This analysis highlights the need for governments, organisations, and society to tackle the stigma surrounding menstruation to provide adequate care to people who suffer from dysmenorrhea