Adrián Horváth

55792323900

Publications - 8

Enhancing Supply Chain Safety and Security: A Novel AI-Assisted Supplier Selection Method

Adrián Horváth József Pap Judit Bilinovics-Sipos Sándor Remsei Tamás Zelles Csaba Makó Zoltán Baracskai

Publication Name: Decision Making Applications in Management and Engineering

Publication Date: 2025-04-01

Volume: 8

Issue: 1

Page Range: 22-41

Description:

The "Make or Buy" decision and the supplier selection are critical steps for the efficient operation of companies' supply chains. Safety and security are paramount considerations, especially in industries like logistics, where supply chains are vulnerable to external threats and disruptions. In this scientific article, we present a novel Artificial Intelligence (AI)-assisted supplier selection method that significantly enhances the safety and security of suppliers. During our research project, we have created an expert system and a corresponding knowledge base with the relevant rules to support supply chain decision-makers in selecting logistics service providers for warehousing services. The foundation of the AI-assisted supplier selection method is advanced data analytics and the application of expert systems, enabling companies to evaluate potential suppliers in detail from a safety and security perspective. The applied expert systems can identify potential risks and make predictions about supplier performance in the future. In the turbulent environment of the global supply chain, selecting long-term partners like warehousing services providers is critical for the success of the organization. A wrong supplier selection can hardly be reversed in warehousing services, as the cost of change is usually high. The article demonstrates the practical application of the expert system-assisted supplier selection method in a real-world supply chain environment and thoroughly analyzes the achieved results and advantages. The results show that the expert system-assisted method not only increases supplier safety and security but also contributes to improving the efficiency and sustainability of the supply chain. This article provides valuable guidance and solutions for companies looking to enhance their supplier selection using expert system technologies, thereby increasing the safety and security of their supply chains.

Open Access: Yes

DOI: 10.31181/dmame8120251115

Cognitive-Biased Decision on Courier Express Parcel Market and the Effect of Narratives

E. Süle Adrián Horváth Csilla Bartucz

Publication Name: Logistics

Publication Date: 2025-03-01

Volume: 9

Issue: 1

Page Range: Unknown

Description:

Background: Extensive research highlights the economic benefits of collaboration among parcel delivery service providers, yet mutually advantageous cooperative arrangements remain limited in Hungary’s online shopping sector. Service providers typically prefer to operate independently rather than cooperate with competitors. However, the COVID-19 pandemic significantly altered industry dynamics, leading to increased collaboration. Methods: Against this backdrop, this study explores two key research questions. First, it examines the role of economic narratives in shaping market dynamics. Second, it investigates the cognitive biases influencing decision-makers during the pandemic, based on an analysis of Hungary’s parcel delivery sector. Semi-structured interviews were conducted with key actors in the logistics industry, and the data were analyzed using abductive thematic analysis. Results: The findings reveal that specific economic narratives, such as those emphasizing efficiency and safety, indirectly influenced market mechanisms during the COVID-19 pandemic. Notably, the shift in consumer demand towards contactless parcel lockers created new incentives for collaboration. Additionally, this study demonstrates that decision-makers exhibited cognitive biases such as risk aversion, which affected their willingness to cooperate. Conclusions: The research concludes that strong economic incentives can override these biases, fostering collaboration among service providers.

Open Access: Yes

DOI: 10.3390/logistics9010029

MILP models of a patient transportation problem

Tamás Hajba Adrián Horváth Martin Tóth

Publication Name: Central European Journal of Operations Research

Publication Date: 2024-12-01

Volume: 32

Issue: 4

Page Range: 903-922

Description:

With ageing societies and increasing number of patients, there is a growing need for quality services that help transporting non-urgent patients to hospitals. In logistics, patient transportation problems are usually modeled as a dial-a-ride problem. In a Dial-a-Ride problem, a fleet of vehicles is providing the delivery services between the loading points and the delivery destinations. The demands are known in advance. In most cases the total travel distance of the vehicles is to be minimized. In this paper, we consider a specific dial-a-ride problem, where a single vehicle is used to transport patients to the same hospital. In determining the optimal route, the multiple and different travel needs of patients, such as their maximum travel time, are also taken into consideration. We introduce 4 different mixed integer linear programming models of the routing problem. Finally, the efficiency of the four models was compared using some real-life problems by solving them with a commercial solver.

Open Access: Yes

DOI: 10.1007/s10100-023-00902-z

Understanding Determining Factors: Purchasing Decisions

E. Süle Adrián Horváth Judit Bilinovics-Sipos

Publication Name: Lecture Notes in Mechanical Engineering

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: 250-256

Description:

The paper aims to highlight the lack of usage of knowledge-based expert systems in purchasing decisions in the context of hybrid corporate reality. We use the transdisciplinary approach in our work, which is essential to examine the problem that occurs in the reality. While reviewing publications containing the keywords “Cognitive bias” and “Supplier selection”, we focused on the methods used. The examined methods in the pooled papers are mainly based on arithmetic and rank the possibilities without considering the available expert knowledge then and there. Afterwards, we propose a solution beyond analyzing the data measured in the past; in addition, the decision-maker, their mental model, and their knowledge is considered. We assume that the effects of cognitive biases are more readily identifiable when using expert systems in considering the decision-maker’s opinions in connection with the actually applied rules in making decisions. In addition to seemingly objective solutions, in our experiment, we propose that by using past cases with known results, complex rules, which are based on the expert’s knowledge, can be simplified without changing the results of decisions in purchasing.

Open Access: Yes

DOI: 10.1007/978-3-031-38165-2_30

Assigning Metaheuristics to a Logistics Problem: a Novel Classification System for Algorithms and Problems

Adrián Horváth Tamara J. Bíró

Publication Name: Chemical Engineering Transactions

Publication Date: 2024-01-01

Volume: 114

Issue: Unknown

Page Range: 1003-1008

Description:

Metaheuristic algorithms applied to NP-hard problems are proven effective techniques in the field of optimization to ensure a good result within an acceptable calculation time. However, finding a suitable technique for optimizing a complex problem is not an easy task since there are hundreds of methods. The majority of metaheuristic research is characterized by developing a new algorithm for a task or modifying or improving an existing technique. The reuse of metaheuristics is small compared to the fact that up to 30+ new procedures can be presented in the scientific community every year. Metaheuristic algorithms have already been grouped in countless ways, but not based on their components and structural elements, which are responsible for the basic optimization performance of the given method. The grouping of the problems to be solved is also not typical in terms of which method can be used to solve them effectively. This paper contributes to filling this gap by introducing a novel classification system for algorithms and problems in terms of variables or based on the type of task. Two main categories were distinguished for both logistic tasks and metaheuristic algorithms: discrete and continuous. Linking the nature of the variables between the task and the algorithm is a significant step forward in choosing an efficient metaheuristic with a high probability for a logistics problem. This can increase the efficiency of solving logistics problems and expand the use of the latest optimization techniques.

Open Access: Yes

DOI: 10.3303/CET24114168

Effects of Cognitive Biases and Their Fuzzy Measure During Freight Transportation

P. Földesi Adrián Horváth Eszter Sós

Publication Name: Lecture Notes in Logistics

Publication Date: 2023-01-01

Volume: Unknown

Issue: Unknown

Page Range: 29-43

Description:

Cognitive biases affect all aspects of our lives, including the decision-making process related to the routing of freight transport. In the process of using human-machine systems, people upload rational and objective algorithms in order to obtain the best possible results in the route planning process. Nevertheless, during the route choice process, human reasoning, based on experience and assumptions, overrides the choice of the machine, that is, cognitive biases appear in the decision-making processes. For this reason, we investigate how an objective system of interests becomes a cognitive bias during the process of making decisions related to the route choice of freight transport by motor vehicle. Furthermore, we present a methodology to estimate fuzzy measures of route-related deviations concerning time and distance, which may be indicative of the emergence of cognitive biases.

Open Access: Yes

DOI: 10.1007/978-3-031-28236-2_3

The impact of data accuracy for efficient and feasible routing plans

Adrián Horváth

Publication Name: Urban Freight Transportation Systems

Publication Date: 2019-01-01

Volume: Unknown

Issue: Unknown

Page Range: 101-114

Description:

Today, more and more problems, such as labor shortages, customer expectations, strict legal environment, and traffic jams, are challenging logistics service providers. Based on practical experience, a prerequisite for efficient distribution is the accurate routing. For this, however, it is essential to use accurate data. This chapter summarizes and presents the most important data needed for efficient routing and the accuracy classes of data. Then, through an example of a logistics service provider’s data, it details the required data and their typical accuracy. With this data and the widely used routing software Paragon, the results of the routing will be compared. Finally, this chapter summarizes the relationship between the accuracy of the data and the usability of the plans. On this basis, proposals for logistics service providers to support efficient operation are made.

Open Access: Yes

DOI: 10.1016/B978-0-12-817362-6.00006-9

Reducing packaging waste by GIS applications

Adrián Horváth Ákos Mojzes Gábor Takács

Publication Name: Green Design Materials and Manufacturing Processes Proceedings of the 2nd International Conference on Sustainable Intelligent Manufacturing Sim 2013

Publication Date: 2013-01-01

Volume: Unknown

Issue: Unknown

Page Range: 443-447

Description:

In the 21st century, the role of electronic gadgets has reached an unexpected limit where they can literally support every aspect of our lives. Not only have the variety of their knowledge-base and the services they provide reached surprising high levels which are now able to support mobility around the globe, but also these gadgets have created new possibilities to measure, collect and save data. The purpose of this article is to present current packaging methods, but also to investigate and specify the actual stress on our products so that we can quantify the real exposure we want to avoid. The importance of this investigation is that if we could find a method to measure and quantify the correct data of the actual stress, it would provide a effective base for reducing the quantity of the packaging materials used. This is especially the case of those products transported on pallets and therefore we could significantly reduce not only the quantity of the base material used for packaging but also the amount of the left over waste resulting from packaging material globally. As an addition to all the above mentioned factors, the topic also gives an interesting perspective on how the savings on the packaging materials could reduce the cost of these products and so provide companies a way to serve their clients in a more cost effective way and an option to offer their products for a much cheaper price and hence gain a larger market share. © 2013 Taylor & Francis Group.

Open Access: Yes

DOI: 10.1201/b15002-86