This paper provides a systematic overview of machine learning methods applied to solve NP-hard Vehicle Routing Problems (VRPs). Recently, there has been great interest from both the machine learning and operations research communities in solving VRPs either through pure learning methods or by combining them with traditional handcrafted heuristics. We present a taxonomy of studies on learning paradigms, solution structures, underlying models, and algorithms. Detailed results of state-of-the-art methods are presented, demonstrating their competitiveness with traditional approaches. The survey highlights the advantages of the machine learning-based models that aim to exploit the symmetry of VRP solutions. The paper outlines future research directions to incorporate learning-based solutions to address the challenges of modern transportation systems.

This paper presents a comprehensive survey of the methodologies and challenges associated with the Vehicle Routing Problem (VRP), focusing on the uncertainties that impact routing decisions in real-world logistics and transportation scenarios. Traditional VRP models often assume static and deterministic conditions, which do not fully capture the complexities of actual logistics operations. This paper categorizes uncertainties into demand variability, travel-time fluctuations, and other dynamic factors, such as service-time variability and vehicle breakdowns. It reviews various approaches to addressing these uncertainties, including dynamic VRP models and the application of reinforcement learning in stochastic environments. The research methodology includes a systematic review of articles published in recent years, emphasizing influential research at the intersection of VRP and uncertainty. The findings highlight the importance of bridging theoretical advances with practical applications to enhance the robustness and adaptability of VRP solutions. The paper concludes by advocating for continued research in this area to improve operational efficiency and service reliability in logistics.

Many exact algorithms, heuristics, and metaheuristics have been proposed to solve the Vehicle Routing Problem with Drones, which involves using a fleet of trucks and drones to fulfil customer orders in last-mile delivery. In this study, the problem is formulated using the Markov Decision Process, and a Reinforcement Learning (RL) based solution is proposed. The proposed RL model is based on an attention-encoder and a recurrent neural network-decoder architecture. This approach enhances coordination by determining which vehicles should visit specific customers and where vehicles can rendezvous, effectively leveraging drones and reducing the overall completion time. The RL model has demonstrated competitive performance compared to benchmark algorithms through extensive experiments.

Artificial intelligence (AI) is increasingly transforming credit approval processes, enabling financial institutions to assess risk more efficiently and at greater scale. As these systems become more embedded in lending decisions, concerns around fairness, bias, and accountability have grown significantly. Many of these concerns stem from the use of historical data, proxy variables, and model optimization choices that can unintentionally reinforce existing social and economic inequalities. This work presents a systematic overview of the types and sources of bias in AI - driven loan approval systems and critically examines how machine learning techniques attempt to address them. It also highlights emerging solutions, including explainable AI, federated learning, human-in-the-loop frameworks, and intersectional fairness approaches. Despite ongoing advancements, unresolved challenges remain - particularly the need for dynamic fairness monitoring and for addressing intersectional biases affecting individuals from multiple marginalized groups. To bridge these gaps, the paper emphasizes the importance of interdisciplinary collaboration among AI developers, regulatory bodies, and social scientists. It advocates embedding fairness as a core design principle in the development and deployment of future AI systems. Overall, this study contributes to the growing effort to develop more transparent, inclusive, and socially responsible financial technologies.

This research presents an extensive investigation intorecommendation systems pertinent to career guidance, encompassing jobmatching, education, and skill development applications. The study rigorouslyexamines methodologies, algorithms, and data sources integral to these systems,evaluating their strengths and limitations. It thoroughly explores evaluationmetrics, real-world case studies, and emerging trends, emphasizing challengeslike data sparsity, scalability, and fairness.Furthermore, the paper provides a comprehensive analysis of machinelearning (ML), deep learning (DL), and reinforcement learning (RL) algorithmswithin recommender systems. By illuminating their strengths, applications, andconstraints, the study highlights the intricate interplay of these algorithms withinrecommendation systems. It addresses challenges including cold-start issues, thestability-plasticity balance, and user satisfaction, offering insights intonavigating these complexities.This research serves as an indispensable guide for researchers andpractitioners alike, providing comprehensive insights into machine learning,deep learning, and reinforcement learning algorithms' roles within careerrecommendation systems. It underscores the significance of overcominginherent limitations and advocates for innovative solutions to enhance thesesystems' effectiveness and applicability in real-world scenarios.

This paper examines how academic staff access and use e-books, and what features they expect from a future digital library platform. Based on survey results, the study reveals that most respondents rely on informal sources, while official databases are used less frequently. At the same time, there is strong demand for key functionalities such as access to a wide collection of e-books, quiz generation, personalized recommendations, and tools for tracking student performance. In addition, the paper provides a comparative review of existing platforms—Perlego, QuizBot, Bookmate, Khan Academy, and Scopus—highlighting both their strengths and limitations, particularly with respect to language support and integration. Taken together, the survey findings and platform analysis underscore the need for a unified adaptive platform that connects publishers, libraries, and users, thereby enhancing accessibility, interoperability, and effectiveness in digital learning.