Applied Mathematics and Computational Intelligence (AMCI)

Visualization of monotonic shaped data by a rational cubic Ball

wan nurhadani wan jaafar — 2025-02-17

This paper discusses the monotonicity-preserving curve interpolation of 2D monotone data. A piecewise rational cubic Ball function in form of (cubic numerator /cubic denominator), with four shape parameters is presented. The rational cubic Ball spline has four shape parameters in its descriptions where two of them are constrained shape parameters and remaining two of them provide the freedom to user to easily control the shape of the curve by simply changing their values. The sufficient data dependent conditions are derived for two shape parameters to insure the monotonicity everywhere. Numerical results show that the Ball interpolation scheme is quite efficient and well tested for monotone data.

Developing a Credit Scoring of the SMEs Manufacturing based on Multi Criteria Decision Making (MCDM) Algorithm

Shakila Saad — 2025-02-17

Credit risk is a very important risk to banks since failure of borrowers to make required payment will lead to high non-performing loans. Hence, it is necessary for banks to develop a mechanism to gauge the credit risk of its borrowers. One of the methods is credit scoring. Small and Medium Enterprises (SMEs) are the backbone of the Malaysian economy comprising 98.5% of the total business established in Malaysia. Despite their importance, access to finance is relatively limited. According to banks, lending money to SMEs are risky compared to large companies due to few factors such as less of publicly available information, young and lack of collateral. Hence, this study tried to predict the credit risk of SMEs in Malaysia by developing a credit scoring that combined financial and non-financial criteria. This study proposes a credit scoring method based on MCDM algorithm that will be able to forecast the score of the potential borrowers at a certain time by using the historic information. Result obtained is verified via the comparison with the given credit risk level provided by banks and by measuring the correlation. The correlation value is 0.88640526 indicates the high positive linear relationship.

A Scalar Modification of Three-term PRP-DL Conjugate Gradient Method for Solving Large-scaled Unconstrained Optimization Problems

Muhammad Aqiil Iqmal Ishak — 2025-02-17

Unconstrained optimization problems arise in numerous fields. This study presents the introduction of a hybrid Polak Ribi‘ere-Polyak(PRP)-Dai-Liao(DL) conjugate gradient(CG) method with a modified scalar for the purpose of solving large -scaled unconstrained optimization problems. The proposed method involves the modification of the scalar in the PRP-DL conjugate gradient method in order to improve the performance of the algorithm, specifically when addressing large-scale problems. The convergence analysis of the proposed method is established and proved under the strong Wolfe-Powell line search. Numerical results on various test functions show that the proposed method is more efficient and robust than several existing CG methods. Overall, the proposed method is a new promising CG method for solving unconstrained optimization problems.

Credit Scoring: A Comparison of Machine Learning Models and Their Modifications

Jia Chong Ong — 2025-02-17

This study compares the performance of various machine learning models and their modifications across four benchmark credit scoring datasets to address the absence of comprehensive comparative analyses on multiple combinations of modifications in the credit scoring domain. Models studied include Logistic Regression (LR), Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Random Forest (RF), and Multilayer Perceptron (MLP). Starting from these base models, a series of modiΫications encompassing feature scaling, resampling, feature selection, and hyperparameter tuning are added phase by phase to the previous models, where the optimal method from each modification is determined in each phase based on the accuracy, F1 score, precision, recall, area under the Receiver Operating Characteristic curve, fitting time and prediction time. Findings reveal LR’s suitability for small datasets, while RF and MLP excel in larger ones. Standardization and Min‐Max Scaling are generally effective, with Max‐Abs Scaling enhancing RF. Synthetic Minority Oversampling Technique proves optimal for imbalanced datasets but no resampling is necessary for small balanced datasets. Analysis of Variance and Mutual Information perform similarly without tuning, while Grid Search slightly outperforms Random Search disregarding runtimes. The study concludes by presenting optimal models and alternatives.

Three‐dimensional Rotating Hybrid Nanofluid over a Shrinking Sheet with Velocity Slip

A. F. S. Raman — 2025-02-17

This study deals with three dimensional rotating nanofluid over a shrinking sheet with velocity slip. Similarity transformations have been used for reducing the partial differential equations into a system of ordinary differential equations. The transformed ordinary diffential equations are solved numerically using BVP4C. The effects of Prandtl number Pr, suction parameter S, shrinking parameter λ, rotation parameter ω and slip parameter K on the velocity and temperature fields are presented and discussed in detail. The change in Prandtl number only affects the temperature profile while changing the rotation parameter affects velocity profiles. As the suction parameter rises, it results an increased velocity profile while the increase of slip parameter leads to a reduction in velocity proΫiles. As the Prandtl number, suction parameter, shrinking parameter, rotation parameter, and slip parameter rises, there is a reduction in the boundary layer thickness. This study provides valuable guidance and insights for researchers and practitioners investigating the mathematical or experimental aspects of three‐dimensional rotating hybrid nanofluids with slip effects.

Predicting Market Trends: A Stock Prices Forecasting with Artificial Neural Network

Farah Liyana Azizan — 2025-02-17

Machine learning plays a crucial role in predicting stock prices, as it aids investors in making well-informed decisions amidst the vast array of stocks traded on the stock exchange. The unpredictability of stock price behaviour, influenced by numerous factors, adds complexity to this process. Consequently, numerous studies have explored the use of machine learning for stock price forecasting. However, it is also difficult to predict the behaviour of stock prices due to the uncertainty associated with them. Hence, this study focuses on employing an Artificial Neural Network model as a machine learning algorithm for forecasting stock prices. The model utilizes the daily stock prices of Apple Inc. and Microsoft Corp. gathered from Yahoo Finance. The performance of the model proposed is evaluated using the Root Mean Square Error (RMSE) and Absolute Error (AE) to assess its effectiveness in analyzing the data.

Application of System Dynamics Modelling to Forecast Sustainability of The Coconut Industry in Malaysia

Nurul Nazihah Hawari — 2025-02-17

Ranked 10^th globally among the largest coconut producers, Malaysia considers coconut as its fourth most significant industrial crop. Presently, there's an urgent need to revitalize Malaysia's coconut industry in terms of production. Beyond its role as a versatile food source, coconut presents valuable employment opportunities for farmers and communities. Statistical data reveals that Malaysia's coconut production demonstrated an upward trajectory until 2013, experienced a slight decline from 2014 to 2017, and resumed an upward trend until 2021. This study seeks to forecast the sustainability of Malaysia's coconut industry by employing a system dynamics approach, comprehensively analyzing various facets of the industry scenario. System dynamics utilizes simulation modeling to predict future trends in coconut production, imports, exports, and other relevant factors based on their interrelationships. The model's projections indicate growth in both coconut production and demand during the simulation period. The insights derived from this study can aid the Malaysian Ministry of Agriculture in devising actionable strategies to safeguard the sustainability of the coconut industry in the years ahead.

A Bibliometric analysis for AI-Powered Chatbots

che wan shamsul bahri che wan ahmad — 2025-02-17

This study reports on the bibliometric analysis of AI chatbots from 2004 to 2024 (20 years) from the Elsevier Scopus database. Through bibliographical analysis of 915 Scopus-indexed documents, the review found that this is very recent literature, with over 98.46% of the relevant documents published since 2016. The contributions of institutional publications by affiliation showed that University of Toronto had the highest number of publications. In this bibliometric analysis, we examine the application of AI-powered chatbots across various domains, focusing on their potential for service enhancement and the challenges associated with their implementation in universities and higher education environment. By reviewing selected research articles, we identify trends, patterns, and key contributors in this expanding field. Notably, AI chatbots offer numerous advantages, such as efficiently handling user inquiries, which are relevant across multiple sectors. We ensure the scientific validity of the study and provide a concise analysis of the existing literature. This bibliometric analysis aims to contribute to the knowledge base and facilitate discussions and planning for the effective deployment of AI chatbots in different sectors and also in university environment in future. In conclusion, this research offers practical recommendations to policymakers, industry leaders, and technology developers on the utilization of AI chatbots to maximize their positive impact and foster supportive environments across different industries in future.

Predicting Risk of Financial Distress using Grover’s Model: A Case study in Malaysia Companies

Chin Wen Wei — 2025-02-17

A bankruptcy prediction is one of the main critical problems for financial decision-makers. In this study, we aim to measure the risk of 5 Malaysian companies' financial failures through Grover's model and further investigate the accuracy of this model in predicting bankruptcy risk. Purposive sampling was used in this study, with five firms being chosen to be sampled in predicting bankruptcy risk. Meanwhile, the data from 292 US companies is used to test the accuracy of Grover's model in predicting bankruptcy risk. The predicted results are classified into three different zones to indicate different consequences. The predicted results were then compared to the actual data. The result shows that 4 out of 5 companies are predicted correctly with approximately 80% accuracy. The results are corroborated by 292 companies maintaining a 75% accuracy. Conclusively, the computed outcome from the case study suggests that Grover's model effectively predicts bankruptcy risk with an accuracy ranging between 75% and 80%.

A Two-Warehouse Inventory Model for Maximum Lifetime Items Under Supplier's Trade Credit

Zaharaddeen Haruna Aliyu — 2025-02-17

In this study, an inventory model is developed considering deteriorating items that have maximum lifetime in a two-warehouse environment. The dispatching policy adopted is First -in First -out (FIFO) against Last-in First-out (LIFO) due to the fact that freshness of items is considered more important than economic reasons. Trade credit was incorporated into the model to make it more practical. With the help of several realistic cases, cost functions were obtained and as well as numerical example is given as an illustration of the model. From sensitivity analysis, it was found that the bigger the lifetime of an item, the smaller the total cost incurred by the retailer.