3830 research outputs found
Sort by
2023 US Bank Failures: Predicting Insolvency using Text Mining
No full textFailure of banks is one of the significant risks in the financial system that regulators critically need to manage and look after. Using sentiment results of annual reports filed by US commercial banks to the Securities and Exchange Commission (SEC) from fiscal years 2016 to 2020, this paper attempts to create a predictive classification model that would act as a supplement to existing regulatory oversight of bank insolvency risks.
Ensemble models (Random Forest, AdaBoost and Light GBM) have been trained which achieved significant results during testing phase (around 60 to 80% accuracy across the models). When back validated to predict the 2023 SVB bank failure using sample data, the best model (Light GBM) returned results with 81% accuracy
Sentiment Analysis of Ireland Hotel Reviews Using Machine Learning Techniques
No full textGlobal internet usage and widespread acceptance of online review platforms play a vital role in individual and collective decision-making. These platforms are employed by users to express their sentiments based on a particular service they have utilized and write reviews. Moreover, the Ireland hotel business is rapidly developing and advancing and millions of individuals including tourists use the services rendered by these hotels. These tourists express their opinions and experiences in textual form that can be analyzed for business purposes and be useful to the Ireland hotel Industry. In this research, sentiment analysis has been employed to detect and classify sentiment polarity in hotel reviews, and different supervised machine learning techniques which include Support Vector Machine, Naïve Bayes, Random Forest and Logistic Regression were implemented and evaluated using accuracy, precision, recall and F1 score. Logistic regression and support vector machine outperformed the other models with an accuracy of 93%
Investigating the Role of Blockchain Technology in Ireland; Enhancing Trust and Security in Digital Marketing Transactions
No full textThis paper investigates how blockchain technology affects Ireland's online advertising. It concentrates on building trust and safety in internet dealings. By closely looking at how digital marketing is done now, where money goes and trust relationships are involved. The study shows what blockchain could do in future. It highlights how this technology can build openness and trust without the need for a central boss. Even though there are problems with making something big, the study says we need to quickly include blockchain in our systems. This will help us use things such as smart contracts faster than ever before. Working together with experts in digital marketing and blockchain is shown. This stresses the importance of being flexible while dealing with changing situations. The study suggests making rules that can be changed to solve problems and keep up with fast-changing tech standards. This will help make a safe digital marketing world
Exploring the power of machine learning to drive energy efficiency in Halifax, West Yorkshire, England: A predictive energy efficiency model for sustainable and resilient buildings and households
No full textPopulation growth and urbanization have increased building energy demand over the past few decades, which has become linked to environmental issues like climate change, air pollution, and thermal imbalances, which have serious health consequences. Halifax, West Yorkshire, has many homes with energy ratings of D and E, which increases CO2 emissions and depletes energy resources. This study examines energy efficiency in buildings by studying climatic, energy usage, and structural elements that affect energy ratings. The effective analysis and administration of this region remain unknown despite earlier studies. This research develops and assesses six machine learning classification models—SVM, RF, GB, XGBoost, KNN, and ET—to forecast energy ratings in the UK's Energy Performance Certificate (EPC) standard rating scale. Model parameters are optimized, important aspects are prioritized, and computational efficiency is being assessed.Sensitivity and correlation analysis illuminate key factors. Ensemble learning can accurately estimate energy performance, which is promising. This study improves Halifax's building energy efficiency image by suggesting greener energy management practices
Exploring implicit infantilisation of persons with disabilities: The role of attitudes, personality, and contact
No full textThis research address implicit maltreatment of persons with disability. It may stem from infantilisation. This research investigated factors associated with implicit disability infantilisation, specifically personality traits agreeableness, openness to experience, self-reported attitudes, and contact. Using an experimental repeated measures design incorporating correlational aspects, data was gathered online using a disability infantilisation IAT, involving the Mini-IPIP, APPD scale, and demographic questions. Sample (n=85), general population aged 18 or over, non-probability convenience. Participants took significantly longer completing the block incompatible with an infantilising attitude aligning with previous infantilisation IAT. Evaluation of D-scores suggested a small positive infantilisation effect. However, D-scores did not significantly associate with any variable. Limitations suggest self-reported attitudes may not capture biases. Future research should use larger sample, standardised measures, combined with mixed methods approaches to enhance generalisability and gain deeper understanding of nuanced variables. Further refinement of infantilisation IAT can provide insights into contributing factors
Evaluative Quantitative Research on the Success Measurement in the field of Project Management
No full textThis study uses an evaluative quantitative technique to look into the vital project management success assessment area. The report compiles a thorough literature analysis, highlighting central ideas and perspectives influencing project success evaluation. Success indicators in real-world project situations are then experimentally evaluated using a survey-based data-collecting approach that uses the Statistical Package for the Social Sciences (SPSS). The literature study shows many viewpoints on project success that consider time, money, stakeholder satisfaction, etc. The dynamic interaction of various variables gives rise to themes, emphasizing the diverse nature of project results. For this study, project management experts from various sectors participated in a structured survey to collect quantitative data. Using SPSS makes comprehensive data analysis possible, allowing for the discovery of trends, correlations, and patterns in success assessment techniques. The study aims to improve our comprehension of assessing project success using this all-encompassing methodology. A comprehensive assessment of success measures' efficacy and applicability is made possible by combining theoretical ideas and empirical facts. The study's findings provide project managers with practical knowledge and a data-driven basis for improving success evaluation techniques and encouraging better project results
The effect of personality and mind wandering on student attitudes to online learning
No full textThe COVID-19 pandemic had a significant impact on education. Lockdown measures to prevent the spread of the virus led to an immediate shift to online learning. Following the lifting of restrictions, some higher education institutes chose to remain online. Research has shown online learning is not suitable for all learners, with some finding it difficult to maintain engagement. The purpose of this study was to investigate the effects of personality and mind wandering on students' attitude to online learning. 101 participants completed an online survey. Of the Big Five, emotional stability was the only trait to have a significant relationship with student engagement in online learning. Openness to experience had a positive relationship with positive constructive daydreaming. In contrast, extraversion, and conscientiousness both had a negative impact on poor attentional control. Openness to experience was shown to have a significant positive relationship with both deliberate and spontaneous acts of mind wandering, with emotional stability having a negative relationship with spontaneous mind wandering
Revamping restaurant billing system through react JS development
No full textThe restaurant industry is always evolving, aiming to improve the dining experience. Beyond great food and service, smooth and efficient payment processes are crucial. This thesis focuses on restaurant billing systems, highlighting the need for modernization in our digital age. Traditionally, restaurants used manual billing, a slow and error-prone process. With complex menus and various orders, accurate billing was challenging. The solution is a tech upgrade, with this research endorsing the React JavaScript Framework. React, known for speed and user-friendliness, promises to revolutionize restaurant billing. The goal is to eliminate manual billing’s inefficiencies and embrace automation. Introducing React streamlines operations, reducing errors. Automation simplifies bill creation, ensuring precise invoices and custom billing systems using React’s modular approach. Ultimately, this journey aims to improve the customer experience by reducing wait times and billing disputes. This thesis blends real-world data and theoretical insights to explore React’s potential in restaurant billing, emphasizing the importance of technology in enhancing operational efficiency
Investigating the Role of SMOTE Sampling and LIME Interpretability in Enhancing Fraud Detection for E-commerce Platforms
No full textFor many years, researchers have been interested in the problem of fraud detection in the financial sector. Both Depending on the data availability and use cases, supervised and unsupervised algorithms are utilized to detect fraudulent transactions. For the supervised binary classification used in this work, detection of fraud using a real dataset from the e-commerce business Vesta. Since the dataset includes actual data, to maintain the data's secrecy, the majority of the characteristics are hidden. The models for machine learning Specifically, Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosted For detecting fraud, the classifier (XGB) and artificial neural network (ANN) are taken into consideration. This research centred on the two fundamental obstacles to fraud detection, model interpretability and skewed data. A sampling strategy has been utilized to balance the distribution of the target variable since the data is extremely skewed. The main goal of this study is to determine how well the oversampling approach SMOTE sampling can solve the problem of class imbalance that arises in fraud detection. Due to the fact that fraudulent transactions occur far less frequently than valid ones, the class imbalance problem frequently results in inferior model performance. To address this mismatch and improve the overall prediction power of fraud detection models, SMOTE builds synthetic instances of the minority class. This paper examines how SMOTE affects various machine learning algorithms, evaluating its capacity to enhance the identification of fraudulent transactions through thorough testing and performance assessment. Furthermore, this article discusses the interpretability of LIME-based fraud detection algorithms. Although machine learning models are highly predictive, their inner workings are sometimes confusing and opaque. LIME, an interpretable machine learning approach, attempts to fill this gap by providing explanations of model predictions that are simple enough for the average person to understand. By creating locally accurate explanations, LIME increases openness and accountability in the fraud detection process and allows stakeholders to understand the thinking behind the model's decision-making. In the context of fraud detection in the VERSTA dataset, the study assesses how LIME explains the complex interactions between features and outcomes. The effectiveness of models with and without SMOTE sampling was analysed in this study. Except for ANN, it has been seen that SMOTE 2 significantly enhances model performance. The second phase of the investigation involves the models' LIME interpretation. To identify the traits shared by these explanations, the feature significance of the models is compared to these LIME interpretations. The LIME interpretations have been criticized mostly for their consistency and stability. The validity of model-neutral explanations like LIME has been contested by several scholars. An unique strategy for combating fraud in the e-commerce space is presented by the combination of SMOTE sampling and LIME interpretability. The findings of this study shed light on SMOTE's effectiveness in dealing with class imbalance and its consequent impact on model performance. The paper also emphasizes how LIME enhances model interpretability, enabling stakeholders to make wise decisions in light of the model's insights. This paper makes a contribution to the advancement of fraud detection approaches in the complex and dynamic environment of e-commerce by tackling the combined concerns of accuracy and interpretability. In summary, this study provides a thorough analysis of how SMOTE sampling and LIME interpretability interact in the context of fraud detection. The paper highlights the potential of these strategies to strengthen the resistance of e-commerce systems against fraudulent activities through empirical validation on the VERSTA dataset, thereby enabling a more secure and reliable digital marketplac
Personality, self-efficacy, and emotional regulation as predictors of positive and negative mental health
No full textEmotion regulation is a complex process that involves initiating, inhibiting, or modulating one's behaviour in a given situation, responding to the ongoing demands of experience with a range of emotions in a socially tolerable and flexible manner. A correlational study investigated the relationship between personality, emotional regulation, self-efficacy, and mental health. Participants included 138 (male = 51, females = 86, non-binary = 1). Three multiple regression analysis investigated if personality, emotional regulation, and self-efficacy were significant predictors of positive affect, negative affect, and total mood. A significant correlation was found between reappraisal (p < .001), self-efficacy (p <.001), extraversion (p = .037) on positive affect. Neuroticism (p < .001) was a significant predictor of negative affect. Self-efficacy (β = -.25) and conscientiousness (β = -.24) displayed a significant negative correlation with negative affect. Suppression (p< .001) and neuroticism p< .001) were found to be significant predictors of total mood