The bird mating optimizer is a new metaheuristic algorithm that was originally proposed to solve continuous optimization problems with a very promising performance. However, the algorithm have not yet been applied for solving combinatorial optimization problems. Thus, the formulation may not be able to generate a discrete feasible solution. Many continuous algorithms used random-key representation to represent the discrete solution using real numbers or a discrete variant of the algorithm is used to deal with the discrete solution of the problem. However, there is no evidence which methodology is better for solving combinatorial optimization problems. Therefore, this work proposes two variants of bird mating optimizer (random-key bird mating optimizer and the discrete bird mating optimizer), to identify which one is more efficient in solving combinatorial optimization problems. In the first one, we use a random-key encoding scheme, whilst, in the later one, we use crossover (multi-parent) and mutation operators to combine the components of the selected parents to generate new broods. The performance of these algorithms are tested on the travelling salesman problem and berth allocation problem, and are compared with the results of two well-known optimization algorithms: Genetic Algorithm and Particle Swarm Optimization. Experimental results show that the discrete bird mating optimizer is more efficient than the others on all tested benchmark instances. Indeed, it is able to attain the best-known results in some of the BAP benchmark instances. These indicate the applicability and the effectiveness of the proposed discrete bird mating optimizer in solving combinatorial optimization problems.

Bird mating optimizer (BMO) is a population-based metaheuristic that has been recently extended to solve combinatorial optimization problems. Even though the algorithm shows promising performance in solving combinatorial optimization problems, it suffers from slow convergence and poor efficiency which leads to poor solution quality for some problem instances. This is due to the limited capability of BMO in exploiting the search space and identifying more promising regions. Therefore, in this work we propose a hybrid BMO with five single-based metaheuristics: hill-climbing, late acceptance hill-climbing, simulated annealing, iterated greedy heuristic and variable iterated greedy heuristic. Each of these algorithms is used inside the BMO to exploit the search space, and improve the quality of solution generated from the BMO population. This work also compares which one of these five is better for hybridizing with BMO. The performance of these algorithms is tested on two combinatorial problems: travelling salesman problem and berth allocation problem. Experimental results demonstrate that the hybrid algorithm is superior to BMO when applied to both problems and it improved the BMO by 1.13% for BAP and by 4.13% for TSP. Furthermore, the hybrid algorithm is able to match the best-known results for most of the instances. In addition, the proposed hybrid approaches perform well over both tested domains and obtain competitive results when compared to the best-known results that have previously been presented in the scientific literature.

The increasing energy demand, driven by population growth and technological advancements, necessitates a shift from traditional fossil fuel-based power generation to renewable energy systems. Solar photovoltaic panels offer a promising alternative; however, their energy output fluctuations present challenges in maintaining a reliable power source. Accurate estimation of solar energy generation is critical for enhancing the competitiveness of solar power plants and fostering social and economic progress. This paper aims to develop a machine learning model that utilizes meteorological and time-related data to predict solar photovoltaic power generation. It investigates how various factors, such as humidity and seasonal variations, impact prediction accuracy. Three different ML models were used and compared: Support vector regression, XGBoost, and HistGradient Boost. To improve the performance of these models hyperparameter tuning techniques is used. The findings reveal that radiation, humidity levels, and seasonal variations are the most influential factors in predicting photovoltaic solar power generation. Additionally, incorporating seasonal and humidity data can enhance the machine-learning model’s accuracy by 17.9%. XGBoost model outperforms existing methods, achieving the highest accuracy of 95.76% when incorporating humidity and seasonal factors. Its lowest MAPE of 4.23 and highest $R^{2}$ of 99.1. to assess model precision, an uncertainty analysis was performed using p-factor and q-factors. The results confirm model robustness and reliability in predictive performance.

The use of credit cards has recently increased, creating an essential need for credit card assessment methods to minimize potential risks. This study investigates the utilization of machine learning (ML) models for credit card default prediction system. The main goal here is to investigate the best-performing ML model for new proposed credit card scoring dataset. This new dataset includes credit card transaction histories and customer profiles, is proposed and tested using a variety of machine learning algorithms, including logistic regression, decision trees, random forests, multi-layer perceptron (MLP) neural network, XGBoost, and LightGBM. To prepare the data for machine learning models, we perform data pre-processing, feature extraction, feature selection, and data balancing techniques. Experimental results demonstrate that MLP outperforms logistic regression, decision trees, random forests, LightGBM, and XGBoost in terms of predictive performance in true positive rate, achieving an impressive area under the curve (AUC) of 86.7% and an accuracy rate of 91.6%, with a recall rate exceeding 80%. These results indicate the superiority of MLP in predicting the default customers and assessing the potential risks. Furthermore, they help banks and other financial institutions in predicting loan defaults at an earlier stage.