A New Similarity Measure of Picture Fuzzy Sets And Application in pattern recognition

Ngoc Minh Chau, Nguyen Thi Lan, Nguyen Xuan

doi:https://doi.org/10.54216/AJBOR.010101

Financial Technology and Innovation | 2026

Digital Financial Technology in Egypt: Determinants, Barriers, and Machine Learning Evidence on FinTech Adoption and Financial Inclusion

Despite the rapid growth of financial technology in Egypt, the socioeconomic factors influencing the adoption of digital financial services at the household level are still not fully understood. This paper presents an Adoption Prediction Model (APM) of Hybrid FinTech (Hybrid-FinTech) model using binary logistic regression together with ensemble classifiers, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost), which is validated using stratified cross validation. The framework introduces a cross-paradigm agreement criterion that ensures that the rankings obtained by the coefficient and machine learning feature importance are compatible, yielding a dual assessment that didn’t exist in either paradigm alone. Empirical analysis finds that internet access and own mobile phone are the most common structural enablers of FinTech adoption with odds ratios that significantly outperform any of the demographic and income variables. The rate of formal bank account ownership has a strong independent positive impact, which suggests complementarity between digital and traditional financial services. The income, educational and urban-rural gaps are striking, and suggest a deep FinTech divide that cannot be bridged entirely by infrastructure. The strong generalisation that is seen in cross-validation is true for all population subgroups. The findings have direct implications for the National Financial Inclusion Strategy, designed by Egypt, and proportionate FinTech regulation.

groups

Dina K. Hassan mail -

Ahmed K. Metawee mail

link https://doi.org/10.54216/FinTech-I.060102

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2020

Neutrosophy for physiological data compression: in particular by neural nets using deep learning

We would like to show the small distance in neutropsophy applications in sciences and humanities, has both finally consider as a terminal user a human. The pace of data production continues to grow, leading to increased needs for efficient storage and transmission. Indeed, the consumption of this information is preferably made on mobile terminals using connections invoiced to the user and having only reduced storage capacities. Deep learning neural networks have recently exceeded the compression rates of algorithmic techniques for text. We believe that they can also significantly challenge classical methods for both audio and visual data (images and videos). To obtain the best physiological compression, i.e. the highest compression ratio because it comes closest to the specificity of human perception, we propose using a neutrosophical representation of the information for the entire compression-decompression cycle. Such a representation consists for each elementary information to add to it a simple neutrosophical number which informs the neural network about its characteristics relative to compression during this treatment. Such a neutrosophical number is in fact a triplet (t,i,f) representing here the belonging of the element to the three constituent components of information in compression; 1° t = the true significant part to be preserved, 2° i = the inderterminated redundant part or noise to be eliminated in compression and 3° f = the false artifacts being produced in the compression process (to be compensated). The complexity of human perception and the subtle niches of its defects that one seeks to exploit requires a detailed and complex mapping that a neural network can produce better than any other algorithmic solution, and networks with deep learning have proven their ability to produce a detailed boundary surface in classifiers.  

groups

Philippe Schweizer mail

link https://doi.org/10.54216/IJNS.010203

Volume & Issue

Vol. Volume 1 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2020

Implicit Authentication Approach by Generating Strong Password through Visual Key Cryptography

In this era of digitization where literally everything is available at the tip of the finger. Huge amount of data used to flow day in day out, where users used to work with various applications like internet websites, cloud applications, various data servers, web servers, etc. This paper provide idea about access control or authentication used to be acting as first line of defense for preserving data secrecy and its integrity, so far it is learned that the usual login password based methods are easy to implement and to use as well but it is also observed that they are more subjected to be get attacked therefore to preserve authentication on the basis of simple alphanumeric passwords is a challenging task now a days. Hence new methods which bring more strength for authentication and access control are so very expected and desirable.

groups

Dr. Ajay B. Gadicha mail -

Dr. Vijay B. Gadicha mail

link https://doi.org/10.54216/JCIM.010102

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

Financial Technology and Innovation | 2026

FinTech Infrastructure and Cryptocurrency Markets in Southeast Asia: A Systematic Review with Evidence from Indonesia and Malaysia

Indonesia and Malaysia are a perfect example of the global FinTech order: two of the world’s biggest Muslim-majority economies with growing and fast expanding digital financial infrastructure, with different regulatory architectures and at different stages of maturity of the cryptocurrency market. In this paper, a systematic review of 40 peer-reviewed studies on technology infrastructure for financial markets in general, the dynamics and adoption of cryptocurrencies, design of central bank digital currencies, Islamic FinTech, and comparative regulatory frameworks in both countries is presented. The review includes five thematic streams: digital payment infrastructure, connectedness of the cryptocurrency market, CBDC development, CBDC Shariah compliance, and financial inclusion enabled by FinTech. The Key findings indicate that Indonesia, under the guidance of the Otoritas Jasa Keuangan (OJK) since 2023, has more than 30 licensed exchanges and an estimated 15 million retail investors, while Malaysia’s Securities Commission (SC) prioritises investor protection over market breadth, issuing five exchanges with higher levels of integration in Islamic finance. There are three structural challenges in both jurisdictions: the lack of ASEAN-level regulatory coordination, the digital infrastructure gap that remains in rural populations and the lack of a harmonized screening mechanism for assets based on Shariah. The review pinpoints 7 high-priority research gaps and outlines a research agenda for the future, organized in 5 methodological pillars.

groups

Mustafa Musa mail -

Raden Aur Aachman Azakiyullah mail

link https://doi.org/10.54216/FinTech-I.060203

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2020

Red Palm Weevil Detection Methods: A Survey

Many pests affect plants, and these have a negatively affected agricultural production and cause a lack of quality. These causes an economic loses and high poverty rates. Many types of pests infest trees like insects, viruses, bacteria, and harmful parasitic plants. One of the most dangerous insects that infest trees such as [date, canary, sago, oil, coconut, etc…] is the Red Palm Weevil (RPW). RPW is currently considered as a global pest, killing trees, increases the tree temperature and causes water stress. It lays the eggs inside the trunk of the tree and starts feeding on the tissue of the plant, then begins to move inside the tree and still inside it until the tree dies, then begin move to the neighboring plants. The early detection of this destructive weevil is not easy; because the visible infection symptoms appear only when the infection stage is dangerous. There are many detection methods for discovering the infected trees, a Visual Inspection, Acoustic Detection, Chemical Detection, and Thermal remote sensing. In this research, we will discuss the different methods used for the early detection of this harmful weevil.

groups

Hanan Ahmed mail

link https://doi.org/10.54216/JCIM.010103

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2020

Data Mining Algorithms for Kidney Disease Stages Prediction

One of the most common health problems that correlated to serious complications is chronic kidney disease. Early detection and treatment can save it from progression. Machine learning is one tool that used historical data to improve future decision about prediction of chronic kidney disease. The aim of this work is to compare the performance of six different models based on accuracy, sensitivity, precision, recall. In this study, the experiments were conducted on 158 records downloaded from UCI repository. Six algorithms ( K-Nearest Neighbor, Naïve Bayes, Support Vector machine, Logistic Regression, Decision Tree, and Random Forest ) were implemented on data after preprocessing stage. Evaluation of models resulted in Naïve Bayes and Random Forest accuracy 100%, Sensitivity 100%, Specificity 100%, precision 100 %, Recall 100% respectively. It is concluded that Naïve Bayes and Random Forest are better than other models.

groups

Abdelrahim Koura -

Hany S. Elnashar mail

link https://doi.org/10.54216/JCIM.010104

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

Financial Technology and Innovation | 2026

FinTech Lending Default Risk: A Stacked Ensemble Credit Risk Framework with SHAP-Based Interpretability

The quick expansion of digital lending platforms has, you know, put borrower default risk right at the center of attention for FinTech investors, regulators, and researchers too. Even though machine learning is now quite often used for credit risk prediction, many models still focus mostly on predictive accuracy rather than interpretability, and also, single-algorithm setups don’t really take advantage of the extra value you’d get from using several different classifiers together. In this work, we put forward the Stacked Ensemble Credit Risk Framework (SECRF). It’s basically a multi layer architecture that merges base learners—logistic regression, random forest, and gradient boosted trees—then routes them to a meta learner, plus an added layer for SHAP based post hoc interpretation and calibration checkups. Across several evaluation perspectives, SECRF shows solid and fairly stable results, and in cross validated experiments the area under the ROC curve stays higher than what single model alternatives typically deliver. When it comes to what actually drives defaults, loan grade along with interest rate emerge as the main predictors under all estimation setups, which lines up with how credit risk is theoretically priced. At the borrower level, the FICO score and debt-to-income ratio also matter in a clear way, while macroeconomic proxies add extra explanatory signals beyond what individual loan descriptors already capture. The interpretability layer is there on purpose so the approach stays compatible with regulatory requirements, and so credit officers get insights they can act on. Finally, the calibration analysis indicates that SECRF outputs are dependable, especially for risk based pricing and provisioning decisions.

groups

Asifa Iqbal mail -

Shahid Mahmood mail

link https://doi.org/10.54216/FinTech-I.060105

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

Financial Technology and Innovation | 2026

From Connectivity to Use: An Innovation-Conversion Model of Digital Finance Across Developing Economies

Digital connectivity has grown more rapidly than people’s engagement with formal digital finance, creating a policy gap beyond mere device, account and network coverage. This article proposes an innovation-conversion framework to approximate the effectiveness of the enabling conditions to be translated into digital-payment usage. Six crosssections are set up as non-competing predictive specifications, repeated cross-validation, out-of-fold benchmarking, regional stress tests and unsupervised archetype mapping to analyse a harmonized 2024 cross-section of 74 low and middle-income economies. The top performing Elastic Net specification achieved a mean cross-validated R2 of 0.867, an out-of-fold R2 of 0.881, and a mean absolute error of 5.23 percentage points. The signal from account ownership was the predominant one, with additional information coming from mobile internet access, self-reported exposure to internet fraud, and internet-skill constraints. The proposed conversion-gap index defines the economies where the actual use of payments significantly under- or over-performs what is expected given the enabling environment. The positive converters were Mongolia, the Republic of Congo, Lesotho and Venezuela, while the largest negative gaps were in India, Ethiopia, Nepal, Sri Lanka and the West Bank and Gaza. Mature digital-use systems, use lagging access-rich systems, mobile-led transitions and foundational access gaps are four structural archetypes that further distinguish the mature systems. The findings change the perception of financial innovation as a conversion issue: infrastructure is important, but institutional onboarding, accessible accounts, building of trust, security, and capabilities will be the keys to making connectivity a commonplace financial transaction.

groups

Serkan Yilmaz Kandir mail -

Murat Ismet Haseki mail

link https://doi.org/10.54216/FinTech-I.060201

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

Financial Technology and Innovation | 2026

Disparate Impact in FinTech Credit Scoring: A Multi-Group Fairness Audit with Mitigation Analysis

Machine learning credit scoring There is no intentional discrimination in models. They differentiate according to data. Such models, trained on borrower histories binned by income, are known as stratified models. absorb and convert the economic situation of the disadvantaged groups and convert them into differential approval rates that last and does not depend on actual creditworthiness. This paper makes a systematic fairness An analysis of three popular classifiers (logistic regression, On a dataset of digital lending, random forest, and XGBoost. Calibrated against statistics of the US consumer credit market. Deploying four Specific fairness measures for each income, gender and age group, and we observe that there is statistically and economically a disparate impact based on income. The poorest fifth of the population earns. approval rates a whopping two decades lower than the top 20.approval scores 20 percentage points lower than the highest. It is not the case that either quintile or logistic regression are 4/5 adverse.Neither quintile nor logistic regression are 4/5 adverse. The standard decision threshold was used and the impact rule was applied. Neither income reweighting nor threshold calibration can get rid of the bias fully since it doesn’t address the bias directly. sacrificing predictive performance. Threshold calibration alone can get into an approximate parity of approval, but with a price of differential. Error rates that present lenders with equal opportunity issues. The results have direct implications for the deployment of The application of algorithmic credit scoring in new regulation regimes, and This contains the EU Artificial Intelligence Act and the US fair lending law.

groups

Irina V. Pustokhin mail -

Denis A. Pustokhin mail

link https://doi.org/10.54216/FinTech-I.060202

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

American Journal of Business and Operations Research | 2020