Stefan Faulkner, Reza Zandehshahvar, Vahid Eghbal Akhlaghi
et al.
Accurate delivery delay prediction is critical for maintaining operational efficiency and customer satisfaction across modern supply chains. Yet the increasing complexity of logistics networks, spanning multimodal transportation, cross-country routing, and pronounced regional variability, makes this prediction task inherently challenging. This paper introduces a multi-task deep learning model for delivery delay duration prediction in the presence of significant imbalanced data, where delayed shipments are rare but operationally consequential. The model embeds high-dimensional shipment features with dedicated embedding layers for tabular data, and then uses a classification-then-regression strategy to predict the delivery delay duration for on-time and delayed shipments. Unlike sequential pipelines, this approach enables end-to-end training, improves the detection of delayed cases, and supports probabilistic forecasting for uncertainty-aware decision making. The proposed approach is evaluated on a large-scale real-world dataset from an industrial partner, comprising more than 10 million historical shipment records across four major source locations with distinct regional characteristics. The proposed model is compared with traditional machine learning methods. Experimental results show that the proposed method achieves a mean absolute error of 0.67-0.91 days for delayed-shipment predictions, outperforming single-step tree-based regression baselines by 41-64% and two-step classify-then-regress tree-based models by 15-35%. These gains demonstrate the effectiveness of the proposed model in operational delivery delay forecasting under highly imbalanced and heterogeneous conditions.
We study the problem of fairly and efficiently allocating a set of items among strategic agents with additive valuations, where items are either all indivisible or all divisible. When items are goods, numerous positive and negative results are known regarding the fairness and efficiency guarantees achievable by truthful mechanisms, whereas our understanding of truthful mechanisms for chores remains considerably more limited. In this paper, we discover various connections between truthful good and chore allocations, greatly enhancing our understanding of the latter via tools from the former. For indivisible chores with two agents, by leveraging the observation that a simple bundle-swapping operation transforms several properties for goods including truthfulness to the corresponding properties for chores, we characterize truthful mechanisms and derive tight guarantees of various fairness notions achieved by truthful mechanisms. Moreover, for homogeneous divisible chores, by generalizing the above transformation to an arbitrary number of agents, we characterize truthful mechanisms with two agents, show that every truthful mechanism with two agents admits an efficiency ratio of $0$, and derive a large family of strictly truthful, envy-free (EF), and proportional mechanisms for an arbitrary number of agents. Finally, for indivisible chores with an arbitrary number of agents having bi-valued cost functions, we give an ex-ante truthful, ex-ante Pareto optimal, ex-ante EF, and ex-post envy-free up to one item mechanism, improving the best guarantees for bi-valued instances by prior works.
This paper studies the welfare impact of discrete improvements to global public goods in the context of the Global Positioning System (GPS). Specifically, I find that by disabling Selective Availability in May, 2000, and thus significantly increasing the accuracy of GPS, the United States generated at least \$268 million (2000 dollars) of additional welfare gains. To quantify this welfare impact, I apply a difference-in-differences model to the Bureau of Transportation Statistics's Airline On-Time Performance Data in the years 1999 and 2000. I use this model to estimate the time saved per flight attributable to the improved GPS and multiply these time savings by the number of passengers in the ensuing year and their values of time. I conclude by estimating the economic loss from current threats to the provision of satellite-based global public goods.
Spatial public goods games model collective dilemmas where individual payoffs depend on population-level strategy configurations. Most existing studies rely on evolutionary update rules or value-based reinforcement learning methods. These approaches struggle to represent payoff coupling and non-stationarity in large interacting populations. This work introduces Multi-Agent Proximal Policy Optimization (MAPPO) into spatial public goods games for the first time. In these games, individual returns are intrinsically coupled through overlapping group interactions. Proximal Policy Optimization (PPO) treats agents as independent learners and ignores this coupling during value estimation. MAPPO addresses this limitation through a centralized critic that evaluates joint strategy configurations. To study neighborhood-level cooperation signals under this framework, we propose MAPPO with Local Cooperation Reward, termed MAPPO-LCR. The local cooperation reward aligns policy updates with surrounding cooperative density without altering the original game structure. MAPPO-LCR preserves decentralized execution while enabling population-level value estimation during training. Extensive simulations demonstrate stable cooperation emergence and reliable convergence across enhancement factors. Statistical analyses further confirm the learning advantage of MAPPO over PPO in spatial public goods games.
Brett Ashworth, Martin J. du Plessis, Leila L. Goedhals-Gerber
et al.
Background: The pressure to meet sustainability goals in the pharmaceutical industry has resulted in significant obstacles, one of which is accurately calculating greenhouse gas (GHG) emissions across the supply chain.
Objectives: This systematic literature review (SLR) aims to identify the frameworks or methodological approaches for calculating logistics emissions in pharmaceutical supply chains (which includes software), as well as the available energy consumption values and emission intensity factors that are needed to calculate emissions.
Method: This SLR follows the nine-step PRISMA 2020 protocol. Keywords were used to form three different search strings to search for frameworks, energy and emission factors. The review encompassed an analysis of a total of 33 documents.
Results: The findings highlight that no standardised methodological approach is used to calculate the emissions of pharmaceutical distribution. Furthermore, no emission factors specific to pharmaceutical products and few benchmarked energy consumption values are available.
Conclusion: The current lack of a standardised methodological approach within the pharmaceutical industry makes it challenging to quantify the emissions associated with the distribution of pharmaceutical products.
Contribution: This SLR identifies the need for a standardised emission framework and associated emission intensity factors in the pharmaceutical industry. It shows that the distribution of pharmaceutical products produces substantial emissions. Shipping 1 kg of ARV pills from a manufacturer in India to a hospital in South Africa emits 0.88 kg CO2e, while shipping 1 kg of snake antivenom ampoules from a manufacturer in India to a hospital in South Africa emits 207.78 kg CO2e.
Shipment of goods. Delivery of goods, Transportation and communications
Abstract This research examines how firms apply quantity discounts to tied versus untied goods in volume bundles, focusing on shaving razors and shaving cream. Tied goods require joint use (e.g., razors and blades), while untied goods are consumed independently (e.g., shaving cream). We test whether bundling discounts differ across these categories. Market data from major online retailers show consistent discounts for shaving cream bundles but not for razor bundles. Findings indicate quantity discounts are less common for tied goods, highlighting product interdependence as a key factor shaping firms’ pricing strategies.
Obstacles on railroads significantly increase the risk of traveling with a lot of train accidents caused by undetected obstacles. The obstacles disturb both the shipments of goods and the transportation of people leading to delays and damage which then result in substantial financial losses. Following natural disasters, manually locating and removing obstacles is not only time-consuming but also hazardous for the personnel involved. To address these challenges, this paper proposes an object detection system that can be implemented on an aerial drone to detect obstacles on the railway. This approach aims to enhance railway safety, reduce costs, and ensure the timely delivery of essential goods such as food and medical supplies during emergencies.
We revisit the identification of the conduct parameter in homogeneous goods markets. Lau (1982) argues that the conduct parameter is not identified if and only if the inverse demand function is separable, except for a specific separable function. This result has been regarded as an extension of the result in Bresnahan (1982) to more general settings. However, we show that Lau's claim is incorrect and provide a new characterization of the non-identification. Our characterization shows that a demand function with demand rotation instruments is the necessary and sufficient condition for the identification of the conduct parameter. Therefore, our result properly generalizes the role of demand rotation instruments in identifying the conduct parameter, as highlighted by Bresnahan (1982), to more general settings.
The public goods game is a broadly used paradigm for studying the evolution of cooperation in structured populations. According to the basic assumption, the interaction graph determines the connections of a player where the focal actor forms a common venture with the nearest neighbors. In reality, however, not all of our partners are involved in every games. To elaborate this observation, we propose a model where individuals choose just some selected neighbors from the complete set to form a group for public goods. We explore the potential consequences by using a pair-approximation approach in a weak-selection limit. We theoretically analyze how the number of total neighbors and the actual size of the restricted group influence the critical enhancement factor where cooperation becomes dominant over defection. Furthermore, we systematically compare our model with the traditional setup and show that the critical enhancement factor is lower than in the case when all players are present in the social dilemma. Hence the suggested restricted interaction mode offers a better condition for the evolution of cooperation. Our theoretical findings are supported by numerical calculations.
Eduardo V. Stock, Pablo A. Valverde, Juan Carlos González-Avella
et al.
The Optional Public Goods Game is a three-strategy game in which an individual can play as a cooperator or defector or decide not to participate. Despite its simplicity, this model can effectively represent many human social dilemmas, such as those found in the use of public services, environmental concerns, or other activities related to society. In this contribution, we present a comprehensive analysis of the conditions under which spontaneous, sustained cooperation emerges and the characteristics of these cooperative states. Through simulations, we demonstrate the conditions leading to the coexistence of the three strategies in a steady equilibrium or the alternate dominance of each strategy in a rock-paper-scissors fashion. The results identify each of the possible scenarios in terms of two key parameters: the multiplication rate of the public good game (reward) and the size of the group of potential players. We also discuss other details of the game that may influence the appearance of cycles, along with relevant characteristics of these cycles, such as the prevalence of cooperation.
The tragedy of the commons illustrates a fundamental social dilemma where individual rational actions lead to collectively undesired outcomes, threatening the sustainability of shared resources. Strategies to escape this dilemma, however, are in short supply. In this study, we explore how artificial intelligence (AI) agents can be leveraged to enhance cooperation in public goods games, moving beyond traditional regulatory approaches to using AI as facilitators of cooperation. We investigate three scenarios: (1) Mandatory Cooperation Policy for AI Agents, where AI agents are institutionally mandated always to cooperate; (2) Player-Controlled Agent Cooperation Policy, where players evolve control over AI agents' likelihood to cooperate; and (3) Agents Mimic Players, where AI agents copy the behavior of players. Using a computational evolutionary model with a population of agents playing public goods games, we find that only when AI agents mimic player behavior does the critical synergy threshold for cooperation decrease, effectively resolving the dilemma. This suggests that we can leverage AI to promote collective well-being in societal dilemmas by designing AI agents to mimic human players.
Elena Smirnova, Nazim Hajiyev, Irina Glazkova
et al.
Logistics and transport-production processes are critical components in the management of supply chains for enterprises. Increasing demands for the accessibility and efficiency of these processes necessitate further refinement of logistics theory and practice. The primary objective of this research was to establish the interrelationship between the structure and functioning of transport operations within manufacturing enterprises. The application of cluster analysis methods revealed the unique structure of each cluster, reflecting the specificity of transport operations. The obtained results determine the stability of the logistic cluster for a specific type of transport and its impact on overall efficiency. The research also emphasizes the importance of improving the quality of transport-production processes to ensure efficiency in supply chains. Quality and logistics service analysis identified factors that can be enhanced, such as service complexity, responsiveness to unforeseen orders, professionalism of the personnel, and fulfillment of order-related commitments. The conclusions drawn contribute to the development of logistics science and theory, providing practical insights by urging manufacturing companies to implement recommendations for optimizing their transport-production processes and selecting the most effective partners in this context. Thus, the originality of the article lies in expanding theoretical concepts of logistics and defining the specifics of transport-production processes.
Expert judgment has been widely utilized in ship risk assessment. The traditional method is believed to be capable of processing only designated linguistic variables, which fails to capture the degree of expert hesitation in assessing a complex system. A novel model, the bi-independent hesitant fuzzy linguistic term set (BHFLTS), based on the hesitant fuzzy linguistic term set (HFLTS), is proposed to incorporate this hesitation. This paper also identifies ten navigational hazards to maritime autonomous surface ship (MASS) operation based on a literature review. In addition, the BHFLTS approach combined with the technique for order preference by similarity to an ideal solution (TOPSIS) is utilized for hazard assessment and ranking, and with this method, “Collision avoidance decision algorithm malfunction”, “Ship situation awareness system failure” and “Command transmission system failure” are rated as the top three navigational hazards that threaten MASS operation.
Karel Van den Berghe, Tanya Tsui, Merten Nefs
et al.
The circular economy (CE) brings many opportunities, but also many challenges for ports, cities, and their hinterland. The goal of this paper is twofold. First, we embrace the inherent uncertainty of the spatial impact of the CE on ports and cities. We employ scenario methodology to guide us in steering this uncertainty by developing four scenarios. To explore the complexity of these four scenarios, we focus on the Dutch province of South-Holland. This region hosts the port of Rotterdam, the largest port in Europe, and its direct hinterland consists of a dense urbanised region. As such, the four scenarios cannot only shed a light on the future of the port, but also how its relations with its direct urbanized hinterland can potentially change. In two scenarios deglobalisation occurs. The consequences are, on the one hand, that the port's focus changes more to its direct hinterland instead of a global oriented focus. On the other hand, the existing water bound industrial areas in, or nearby cities increase in importance, in contrast to the contemporary pressure to redevelop these into waterfront residential and commercial areas. In other words, port and city/region grow towards each other. The second goal of the paper is to dive into the specific consequences of these scenarios for day-to-day planning practices. By combining micro-economic and AIS shipping data, we discovered the most important terminals and industrial areas for the transition towards a CE in port, city, and hinterland.
Евгения Андреевна Чеботарева, Ирина Андреевна Солоп, Кирилл Владимирович Аношкин
В статье выполнен анализ надежности доставки грузов и доли грузовых отправок, проследовавших по инфраструктуре дороги в установленный срок на сети железных дорог. Рассмотрены вопросы нарушений сроков доставки грузов, систематизированы основные причины нарушения сроков доставки в региональном разрезе на примере Северо-Кавказской железной дороги, обслуживающей порты Азово-Черноморского бассейна и грузополучателей Южного региона. Проведен анализ претензионной работы, в связи с нарушением сроков доставки грузов, рассмотрены вопросы выполнения скорости и сроков доставки грузовых и порожних отправок на Северо-Кавказской железной дороге. Выявлены причины снижения надежности доставки грузов с учетом особенности загрузки транспортной инфраструктуры Юго-Западного полигона. Выработаны механизмы управления сроком доставки на железнодорожном транспорте на базе логистических и информационных технологий, намечены комплексные мероприятия для восполнения допущенного отставания показателя надежности груженых отправок. The article analyzes the reliability of the delivery of goods and the share of freight shipments that proceeded along the infrastructure of the road in a timely manner on the railway network. The issues of violations of the terms of delivery of goods are considered, the main causes of violations of the terms of delivery in the regional context are systematized on the example of the North Caucasian Railway, serving the ports of the Azov-Black Sea basin and consignees of the Southern region. The analysis of the claim work was carried out, in connection with the violation of the terms of delivery of goods, the issues of fulfilling the speed and terms of delivery of freight and empty shipments on the North Caucasian Railway were considered. The reasons for the decrease in the reliability of cargo delivery are identified, taking into account the peculiarities of loading the transport infrastructure of the South-Western range. Mechanisms have been developed for managing the delivery time in rail transport on the basis of logistics and information technologies, and complex measures have been outlined to make up for the admitted lag in the indicator of the reliability of loaded shipments.
Iqra Aslam, Adina Aniculaesei, Abhishek Buragohain
et al.
Last-mile delivery of goods has gained a lot of attraction during the COVID-19 pandemic. However, current package delivery processes often lead to parking in the second lane, which in turn has negative effects on the urban environment in which the deliveries take place, i.e., traffic congestion and safety issues for other road users. To tackle these challenges, an effective autonomous delivery system is required that guarantees efficient, flexible and safe delivery of goods. The project LogiSmile, co-funded by EIT Urban Mobility, pilots an autonomous delivery vehicle dubbed the Autonomous Hub Vehicle (AHV) that works in cooperation with a small autonomous robot called the Autonomous Delivery Device (ADD). With the two cooperating robots, the project LogiSmile aims to find a possible solution to the challenges of urban goods distribution in congested areas and to demonstrate the future of urban mobility. As a member of Niedersächsische Forschungszentrum für Fahrzeugtechnik (NFF), the Institute for Software and Systems Engineering (ISSE) developed an integrated software safety architecture for runtime monitoring of the AHV, with (1) a dependability cage (DC) used for the on-board monitoring of the AHV, and (2) a remote command control center (CCC) which enables the remote off-board supervision of a fleet of AHVs. The DC supervises the vehicle continuously and in case of any safety violation, it switches the nominal driving mode to degraded driving mode or fail-safe mode. Additionally, the CCC also manages the communication of the AHV with the ADD and provides fail-operational solutions for the AHV when it cannot handle complex situations autonomously. The runtime monitoring concept developed for the AHV has been demonstrated in 2022 in Hamburg. We report on the obtained results and on the lessons learned.