3830 research outputs found
Sort by
Portfolio Management For Asset Forecasting Using Recurrent Neural Network
No full textThis thesis examines the use of emerging neural networks to predict future financial asset price movements in a set of futures contracts. To help with our research, we compare ourselves to a simple set Feed Network. We do more research on different networks by considering the different functions that lose purpose and how they affect the performance of our networks. This discussion is expanded by considering the Mass Loss Network. The use of different law functions highlights the importance of
feature selection. We learn about a set of simple and complex features and how they affect our model. This will enable us to take a closer look at the differences between our networks. Finally, we analyse our model gradients to provide more information about the features of our features. Our results show that repetitive networks offer higher specification performance than relay networks
when considering sharpening ratings and accuracy. General features show better results when it comes to accuracy. While the goal of the network is to expand to shards, complex features are selected. Using high-loss networks is successful because we consider achieving high Sharp ratings as our main goal. Our results show better performance than the usual set of benchmarks
Predictive Analytics for Malware Detection in FinTech using Machine Learning Classification
No full textCyber-attacks are a major issue in the FinTech space, and a solution is needed that can provide a fast and effective way of malware detection. This paper aims to use machine learning classification to detect malware on computers using the Microsoft Malware dataset. The research followed Cross Industry Standard Process for Data Mining (CRISP-DM) methodology and comparatively analysed Logistic Regression, Decision Trees, and Naïve Bayes models. Gaussian Naïve Bayes Classifier was the best model with a recall score of 76%. The split of the data that achieved the best result was at 70% train, 30% test. Ensemble
methods were deemed unnecessary as they did not improve the recall score of the individual model. The most important features related to the size of the system on a computer, its build type, and products installed on it. It is recommended that FinTech companies use Gaussian Naïve Bayes modelling for intrusion detection systems
A Regression Based Approach for Prediction of Major League Baseball Game Outcomes
No full textData analytics and statistics have seen increasing usage in professional sports in recent years, with many professional organisations expanding the usage of data analytics to improve team performance. Similarly, organisations adjacent to professional sports, such as gambling and sportsbooks have traditionally been one of the largest groups utilising statistical analysis for sports outcome prediction. With the wealth of data and techniques available now, the question naturally becomes how accurately can the outcome of a sporting event be predicted. This project aims to build and quantify a regression-based
machine learning model for the prediction of the outcome of a game of baseball, first by determining the statistical value of individual players, and then by determining the relative statistical value of the teams they play on. Baseball has traditionally been the most statistically driven professional sport, with over 100 years of complex recorded statistics. However, despite the sheer amount of data available, the simple classification question of which of two teams will win a game between them remains impossible to answer. Existing models from simple Naïve classifiers to complex artificial neural networks have largely been limited to classification accuracies of <60%. The plethora of unquantifiable factors in any sport leads to it surely being impossible to ever definitively solve these problems. The aim of this project is to build an adaptive regression-based model that can be used and further tuned to improve predictive capability as both a classifier and probabilistic predictor. The current version of the model combines a multilinear regression-based model and a logistic regression-based model to produce a predictive model that presents a classification accuracy of 56.6%, an AUC of 0.549, and a Brier Score of 0.244
Hijabi well-being: measured on the stress, resilience, coping and social support scales
No full textThe aims of the study was to measure the psychological well-being of Hijabi women on the stress, resilience, coping and social support scales. Eight hypotheses were analysed to find the effects of the independent variables on the mental well-being of participants. Participants included Muslim women aged 18 years and above. To measure stress levels Perceived Stress Scale-14 was used. The Brief Resilience Scale was used to measure resilience. The Brief Resilient Coping Scale was used to measure coping levels and the Multidimensional Scale Perceived Social Support was used to measure the social support available to participants. Simple and multiple regression analyses were used along with independent sample t-test and a non-parametric equivalent of independent t-test was used to analyse the hypotheses. The results showed that age was not a significant predictor of stress, resilience and coping scores. Resilience was shown to be a strong predictor when combined with other variables for analyses
A qualitative study: has sea swimming increased adults’ perceived physical and mental health benefits during COVID 19 lockdown?
No full textA qualitative study was used to investigate an increase in the perceived mental and physical health benefits of sea swimming in adults during the COVID-19 lockdown. Semi-structured interviews were conducted on 5 sea swimmers and their experiences were analysed using Braun and Clarke’s (2019) thematic analysis (N=5). Ages ranged from 21 to 66 with a mean age of 46.6. Open-ended questions were used to ensure a detailed personal account of each participant was captured. Results indicate a positive mental and psychosocial aspect of sea swimming however limited findings were recorded for physical benefits from this cohort. One weakness to be considered is all participants were female. For future research, to ensure gender balance, a more equal inclusion of all sexes to be considered. Limitations of the study clearly emphasise the need to explore wider community and social support services that participants might be using to verify sea swimming results
Impact of Covid-19 pandemic on the Irish population: factors influencing compliance & belief in Covid
No full textThe aim of this study was to investigate the impact that the Covid-19 pandemic has had on the Irish population, testing their satisfaction with life, perceived stress, fear of Covid, Covid compliance, and belief in conspiracy theories about covid-19. Data from 151 (females 104, males 45, prefer not to say= 2) participants was collected through an online self-report survey. In this survey, participants were asked to complete a total of five questionnaires: The Fear of Covid Scale (Ahorsu et al., 2020), The Covid Compliance Scale (Köse et al., 2021), The Perceived Stress Scale (Cohen et al., 1994), The Satisfaction With Life Scale (Diener et al., 1985), and the Compliance and Belief in Conspiracy Theories Scale (Pavela et al., 2021). Results found significant positive correlations between fear of Covid and perceived stress, and fear of Covid and compliance with Covid health/safety measures. Results also found a negative correlation with fear of Covid and satisfaction with life. Testing between groups found that: females were significantly more fearful of Covid and compliant with health/safety measures than males. It was also found that there was no particular age group that were more fearful of covid. Participants that had not tested positive for Covid were significantly more fearful of it than those that had. All data used in this study was collected quantitatively through an online Google Form survey over the period of roughly one month. Important conclusions drawn from this study indicate a need for more focused health and safety campaigns particularly amongst the male population. Males were identified as being less compliant and more likely to take risks rather than comply with public health advice
Cryptography based Cloud Security in UK’s Banking System
No full textCloud computing is a rapidly expanding technology that every business today aspires to
incorporate into its operations to increase profitability and scalability. Because the public's
use of financial transactions is growing by the day, cloud computing is now being used in the
banking sector. Cloud banking has provided the most cost-effective money transmission with
the highest level of security. One of the key reasons for cloud computing's rapid expansion in
the banking sector is the highly secured environment.
The objective of this research is to render a more elaborated and complete understanding of
the issues and challenges related to Cloud security along with review study on various data
encryption schemes proposed for secure data sharing in Cloud. The critical literature analysis
provides more elaborated and complete understanding of the issues and challenges related
to Cloud security and provide major research directions for future to the researchers in
concerned areas.
In this study cloud computing in banking has been analysed in detailed manner with respect
to the Retail banking in UK handling customers data and transactions, secured accesses,
advantages of secured cloud banking using encryption and decryption of data through the
Cryptography.
This study focuses on a critical component without which the entire system may collapse i.e.,
security! What are the most important components to secure the application? What impact
will cloud computing have on our computing experience? What role does cryptographic
encryption and decryption play in this? How do they function, and how will they keep our
data safe
Newly Qualified Irish Primary School Teachers’ Experiences and Understandings of Reinforcement and Punishment
No full textThe Irish education system has had many considerable changes within the past two decades. Initial teacher education has considerably lengthened in duration. Behaviour management models utilised within the education system have also shifted, from punitive towards reinforcement-based procedures. There has been a significant amount of research regarding the preparation provided by ‘Initial Teacher Education’ (ITE) programmes in the Irish context. Much of this research highlighted findings regarding how underprepared teachers are in the area of behaviour management. Interestingly, however, there has been little research on preparedness since the ITE programmes have recently lengthened in duration. Therefore, this qualitative research aimed to answer the question: What are the experiences and understandings of Irish newly qualified primary school teachers (NQTs) in the area of punishment and reinforcement within the context of behaviour management? Four semi-structured interviews with newly qualified teachers were conducted. Thematic analysis of transcripts indicated four key themes: ‘Learning of behaviour management’, ‘Reinforcement’, ‘Punishment’, and ‘Establishment of behaviour management’. The findings indicate, though provided with various learning opportunities, newly qualified teachers lack in their understanding of the terms reinforcement and punishment, despite clear uses of both in the classrooms. The NQTs had a clearer concept of the term reinforcement, in comparative to that of punishment. Although participants were largely unaware of the definition of punishment, and often evidently disapproving of its use, there were clear uses of punishment procedures by NQTs in the findings of this study. This study indicated the need to scrutinise education in the area of behaviour management at both initial teacher education and newly qualified teacher levels. Further studies investigating the impact of varying methods of preparation for effective behaviour management may be beneficial. Further exploration of the causal links between NQT self-efficacy and the selection of reinforcement or punishment is also recommended
Generation Z – A quantitative study into their motivation in the workplace in Ireland
No full textMotivation in the workplace has been the subject of many studies over the time, and as a
consequence of this, some theories were being developed on the subject. The most famous of
these theories are the ones developed by Maslow and Herzberg, known as the hierarchy of needs
and two factors, respectively. The different generations that have emerged, are the constant
subject of studies, which aim to identify their characteristics and their motivations, with the
Generation Z it would not be different. Due to this, this quantitative study aims to identify
whether the theories of motivation, specifically those developed by Maslow and Herzberg can
be applied to the motivation of Generation Z. To achieve this objective, a questionnaire with
questions that sought to identify Generation Z motivation was conducted and answered by 45
participants. The findings of the data collected show that the theory developed by Herzberg can
be partially applied to Generation Z, while Maslow's theory has no applicability to the motivation
of this generation. Further research is needed to discuss other theories
The ethics of classifying the world: from library catalogues to AI
No full textThis paper reports on an initial exploration of knowledge classification ethics: What are the important ethical issues in how we classify knowledge and what kind of cognitive, cultural and social impacts may they have? An important part of Knowledge Management is the classification and organisation of knowledge to make it findable and reveal connections in related subjects. Discussion on the ethical aspects of this issue have recently been brought to the fore in both Library and Information Studies (LIS), in terms of objections to Library classification terms, and also in AI which can classify data using data sets which themselves reflect existing injustices and bias. The ethical implications of both types of knowledge classification can be better understood when the classification ethics debate in LIS and AI are used to inform each other.Findings include that AI provides clarity on measuring adverse outcomes whilst LIS provides nuance on the potential cultural and psychological harm of inappropriate terminology and inaccurate positioning within ‘worlds of knowledge