On the Pre-pandemic time most of the projects were traditional financial banking methods, that means the biggest companies had have receive 85%, leaving only the 15% for the Small and medium-sized enterprises (SMEs), ...
详细信息
ISBN:
(纸本)9783031456473;9783031456480
On the Pre-pandemic time most of the projects were traditional financial banking methods, that means the biggest companies had have receive 85%, leaving only the 15% for the Small and medium-sized enterprises (SMEs), in the pandemic period financial risk increased and trying to figure out how to survive the biggest companies update them technology for e-commers but SMEs did not have enough money to do it, for that reason they found a solution on fintech technologies. As a result, in the post pandemic era, fintech companies began to have a huge relevance not only as a technology supplier but also as financial provider. The main reason of this research is to find out if Fintech companies could be provider for projects to big companies and SMEs, the outcome shows that project managers of different industries see e-money as a secure payment method and with the fintech establishment on the economic scene they begin to feal more comfortable with the idea of using fintech companies as financial provider for projects in them companies. This research was carried out under the descriptive method, The tool selected to collect information was Google Forms, in this tool a multiple-choice survey was created, and email was sent with access to the survey. The results allow us to understand that they can be a permanent and reliable source to finance projects of different types of industries.
Forecasting the creditworthiness of customers in newand existing loan contracts is a central issue of lenders' activity. Credit scoring involves the use of analytical methods to transform historical loan applicati...
详细信息
ISBN:
(数字)9783031456428
ISBN:
(纸本)9783031456411;9783031456428
Forecasting the creditworthiness of customers in newand existing loan contracts is a central issue of lenders' activity. Credit scoring involves the use of analytical methods to transform historical loan application and loan performance data into credit scores that signal creditworthiness, inform, and determine credit decisions, determine credit limits, and loan rates, and assist in fraud detection, delinquency intervention, or loss mitigation. The standard approach to credit scoring is to pursue a "winner-take-all" perspective by which, for each dataset, a single believed to be the "best" statistical learning or machine learning classifier is selected from a set of candidate approaches using some method or criteria often neglecting model uncertainty. This paper empirically investigates the predictive accuracy of single-based classifiers against the stacking generalization approach in credit risk modelling using real-world peer-to-peer lending data. The findings show that stacking ensembles consistently outperform most traditional individual credit scoring models in predicting the default probability. Moreover, the findings show that adopting a feature selection process and hyperparameter tuning contributes to improving the performance of individual credit risk models and the super-learner scoring algorithm, helping models to be simpler, more comprehensive, and with lower classification error rates. Improving credit scoring models to better identify loan delinquency can substantially contribute to reducing loan impairments and losses leading to an improvement in the financial performance of credit institutions.
Public and private institutions have invested in IT to increase their information security. Along with investments, the human factor is dominant. In that sense, countries have also implemented their own Computer Secur...
详细信息
ISBN:
(数字)9783031456428
ISBN:
(纸本)9783031456411;9783031456428
Public and private institutions have invested in IT to increase their information security. Along with investments, the human factor is dominant. In that sense, countries have also implemented their own Computer Security Incident Response Teams (CSIRTs), whose main objective is to minimize and control the damage in case of a security breach. In the case of the Chilean government, with its CSIRT, they propose newguidelines for IT standards related to cybersecurity in the country's gaming casinos. This incorporation includes creating internal policies, procedures, protocols, and procurement. The objective of this article is to design a model for creating a cybersecurity awareness and education campaign based on the recommendations of the National Institute of Standards and Technology (NIST) and ISO 27001. The methodology consists of the evaluation of these alternatives and the declaration of 5 preliminary stages. On this occasion, we evaluated the first of them, evaluating all the internal workers of the company to form the subsequent initiatives.
The latest technological advances drive the emergence of countless real-time data streams fed by users, sensors, and devices. These data sources can be mined with the help of predictive and classification techniques t...
详细信息
ISBN:
(数字)9783031456428
ISBN:
(纸本)9783031456411;9783031456428
The latest technological advances drive the emergence of countless real-time data streams fed by users, sensors, and devices. These data sources can be mined with the help of predictive and classification techniques to support decision-making in fields like e-commerce, industry or health. In particular, stream-based classification is widely used to categorise incoming samples on the fly. However, the distribution of samples per class is often imbalanced, affecting the performance and fairness of machine learning models. To overcome this drawback, this paper proposes Bplug, a balancing plug-in for stream-based classification, to minimise the bias introduced by data imbalance. First, the plugin determines the class imbalance degree and then synthesises data statistically through non-parametric kernel density estimation. The experiments, performed with real data from Wikivoyage and Metro of Porto, show that Bplug maintains inter-feature correlation and improves classification accuracy. Moreover, it works both online and offline.
Data management solutions became highly expensive and ineffective mainly due to the lack of transparent processes and procedures to measure and provide clear guidance on the steps needed to implement them. The organiz...
详细信息
ISBN:
(数字)9783031456459
ISBN:
(纸本)9783031456442;9783031456459
Data management solutions became highly expensive and ineffective mainly due to the lack of transparent processes and procedures to measure and provide clear guidance on the steps needed to implement them. The organizations and specialists agree that the only manner solve the data management issues requires the implementation of data governance. Many of those attempts had failed previously because they were based only on IT, with rigid processes and activities frequently split by systems or the areas supported by systems and their data. It shows that Data governance has been acquiring significant relevance. However, a consensus or even a holist approach was not achieved so far. This paper that is part of an ongoing thesis research that aims to identify the main gaps and opportunities by summarizing and study the literature consistently and as result at the end of the research it will propose a standard framework for data governance measuring its impact on the Data Governance maturity level before and after its implementation and thus as contribute to the community by trying to mitigate the problems found.
Augmented reality (AR) technology has emerged as a promising tool for enhancing the shopping experience in e-commerce (Alalwan et al. in Int J Retail Distrib Manag 45:458-472, 2017). This research paper provides a com...
详细信息
ISBN:
(纸本)9789819713127;9789819713134
Augmented reality (AR) technology has emerged as a promising tool for enhancing the shopping experience in e-commerce (Alalwan et al. in Int J Retail Distrib Manag 45:458-472, 2017). This research paper provides a comprehensive review of the current state of research on augmented reality in e-commerce. The paper begins with an overview of the history and development of augmented reality technology and its current applications in e-commerce (Cho and Kim in Int J Hum Comput Interact 35:1513-1523, 2019). The paper then reviews the opportunities and challenges of using augmented reality in e-commerce, including the impact on consumer behavior, marketing strategies, and the supply chain. The research methodology used to investigate the research question is also presented, including the sample size, data collection instruments, data analysis techniques, and ethical considerations (Alalwan et al. in Int J Retail Distrib Manag 45:458-472, 2017). The results of the research are presented and interpreted in the discussion section, followed by recommendations for future research and practice.
Digital audio signal reconstruction of a lost or corrupt segment using deep learning algorithms has been explored intensively in recent years. Nevertheless, prior traditional methods with linear interpolation, phase c...
详细信息
ISBN:
(数字)9783031477218
ISBN:
(纸本)9783031477201;9783031477218
Digital audio signal reconstruction of a lost or corrupt segment using deep learning algorithms has been explored intensively in recent years. Nevertheless, prior traditional methods with linear interpolation, phase coding and tone insertion techniques are still in vogue. However, we found no research work on reconstructing audio signals with the fusion of dithering, steganography, and machine learning regressors. Therefore, this paper proposes the combination of steganography, halftoning (dithering), and state-of-the-art shallow and deep learning methods. The results (including comparing the SPAIN, Autoregressive, deep learning-based, graph-based, and other methods) are evaluated with three different metrics. The observations from the results show that the proposed solution is effective and can enhance the reconstruction of audio signals performed by the side information (e.g., Latent representation) steganography provides. Moreover, this paper proposes a novel framework for reconstruction from heavily compressed embedded audio data using halftoning (i.e., dithering) and machine learning, which we termed the HCR (halftone-based compression and reconstruction). This work may trigger interest in optimising this approach and/or transferring it to different domains (i.e., image reconstruction). Compared to existing methods, we show improvement in the inpainting performance in terms of signal-to-noise ratio (SNR), the objective difference grade (ODG) and Hansen's audio quality metric. In particular, our proposed framework outperformed the learning-based methods (D2WGAN and SG) and the traditional statistical algorithms (e.g., SPAIN, TDC, WCP).
This paper intends to study the importance of digital marketing to attract participants to musical events. We use the case of NOS Primavera Sound, and we analysed the 2022 edition, which contemplated 1126 valid respon...
详细信息
ISBN:
(数字)9783031456510
ISBN:
(纸本)9783031456503;9783031456510
This paper intends to study the importance of digital marketing to attract participants to musical events. We use the case of NOS Primavera Sound, and we analysed the 2022 edition, which contemplated 1126 valid responses. To reach our objective we ran a logit model and verified that the sociodemographic characteristics present a different impact on digital marketing tools (when compared to other means of communication). The results of this study established that participants can be influenced to participate in the music festival through various digitalmarketing tools while being sensitive to the two characteristics themselves.
Endometriosis is a complex gynecological condition characterized by the presence of endometrial-like tissue outside the uterus. Diagnosis and management of endometriosis are challenging due to diverse clinical manifes...
详细信息
ISBN:
(纸本)9789819732883;9789819732890
Endometriosis is a complex gynecological condition characterized by the presence of endometrial-like tissue outside the uterus. Diagnosis and management of endometriosis are challenging due to diverse clinical manifestations and lack of definitive diagnostic methods. Medical imaging, particularly ultrasound and magnetic resonance imaging (MRI), has shown potential in visualizing and assessing endometriosis lesions. In this research paper, we review recent advances in machine learning algorithms applied to endometriosis diagnosis, focusing on the importance of training datasets in improving diagnostic accuracy. We analyze the contributions of various studies and discuss the challenges and future directions in this field.
This project aimed to develop a fire and flood risk monitoring system in a data center by applying Internet of Things (IoT) technology. A powerful wireless network was implemented, comprising a microcontroller, two se...
详细信息
ISBN:
(数字)9783031703003
ISBN:
(纸本)9783031702990;9783031703003
This project aimed to develop a fire and flood risk monitoring system in a data center by applying Internet of Things (IoT) technology. A powerful wireless network was implemented, comprising a microcontroller, two sensors and a user interface (ubidots). The sensors periodically transmit data to the microcontroller, which sends this information to a cloud server to be accessible through a user interface. When any of the values of the variables reaches a predefined threshold, an alert is sent to the graphical interface through the microcontroller and the user is alerted.
暂无评论