arXiv subjects

Martijn Mes

Publications and source records attributed to Martijn Mes.

8 recordsLinked to original sources

arXiv2026

Causal Analysis for Time Series Foundation Models

Transitioning from bespoke time series models towards time series foundation models changes the relationship of model and application from one-to-one to one-to-many. This shift introduces concentration risk as many, potentially high-risk, forecasting applications are exposed to the same biases and failure modes of a single time series foundation model. At the same time, this centralization allows for economies of scale in model development and validation. In this study we investigate how biases and failure modes of time series foundation models can be identified before deployment. We propose a causal analysis framework to investigate the ability of a time series foundation model to preserve time series patterns. To achieve this, we intervene on parameterized synthetic time series generators and measure the corresponding change in model output under ceteris paribus conditions. We apply our causal analysis framework to Chronos-2 and TimesFM-2.5 and test them across six distinct time series patterns. We find safe configurations for trend and harmonic oscillation patterns. The results also indicate a bias in both models towards overestimating persistence, sudden failures for both models against the regime switch pattern and failure for TimesFM-2.5 against the energy-release pattern. Our review of the original works for both models indicates that the findings might be explained by the data used for pretraining. We conclude our study with suggestions for further model development, recommendations for application-specific model selection, and a discussion of limitations and further research directions.

cs.LG↗

arXiv2026

Efficient Road Renovation Scheduling under Uncertainty using Lower Bound Pruning

Urban infrastructure degrades over time, necessitating periodic renovation to maintain functionality and safety. When renovation is delayed beyond the infrastructure's remaining lifespan, costly emergency interventions become necessary to prevent failure. Decision makers must therefore balance expected emergency intervention costs against traffic congestion impacts. We formalize this trade-off as a road network maintenance scheduling problem with uncertain deadlines, which presents optimization challenges including computationally expensive evaluation and an exponentially growing solution space. To address these challenges, this paper contributes a hybrid optimization approach combining machine learning with genetic algorithms for large-scale infrastructure renovation scheduling under uncertainty. We formulate the problem as a bi-level multi-objective optimization problem that explicitly accounts for uncertain infrastructure lifespans through probabilistic failure models. We develop a progressive lower bound evaluation method that integrates machine learning surrogate models with a multi-objective genetic algorithm to improve solution quality by enabling more iterations within fixed computational budgets. We demonstrate the method's effectiveness on substantially larger problem instances (76 projects) than previously addressed in the literature, achieving statistically significant improvements across multiple performance metrics by increasing computational efficiency up to 40 times compared to standard approaches.

cs.CE↗

arXiv2025

Deep Learning--Accelerated Multi-Start Large Neighborhood Search for Real-time Freight Bundling

Online Freight Exchange Systems (OFEX) play a crucial role in modern freight logistics by facilitating real-time matching between shippers and carrier. However, efficient combinatorial bundling of transporation jobs remains a bottleneck. We model the OFEX combinatorial bundling problem as a multi-commodity one-to-one pickup-and-delivery selective traveling salesperson problem (m1-PDSTSP), which optimizes revenue-driven freight bundling under capacity, precedence, and route-length constraints. The key challenge is to couple combinatorial bundle selection with pickup-and-delivery routing under sub-second latency. We propose a learning--accelerated hybrid search pipeline that pairs a Transformer Neural Network-based constructive policy with an innovative Multi-Start Large Neighborhood Search (MSLNS) metaheuristic within a rolling-horizon scheme in which the platform repeatedly freezes the current marketplace into a static snapshot and solves it under a short time budget. This pairing leverages the low-latency, high-quality inference of the learning-based constructor alongside the robustness of improvement search; the multi-start design and plausible seeds help LNS to explore the solution space more efficiently. Across benchmarks, our method outperforms state-of-the-art neural combinatorial optimization and metaheuristic baselines in solution quality with comparable time, achieving an optimality gap of less than 2\% in total revenue relative to the best available exact baseline method. To our knowledge, this is the first work to establish that a Deep Neural Network-based constructor can reliably provide high-quality seeds for (multi-start) improvement heuristics, with applicability beyond the \textit{m1-PDSTSP} to a broad class of selective traveling salesperson problems and pickup and delivery problems.

cs.AI↗

arXiv2025

Machine Learning Predictions for Traffic Equilibria in Road Renovation Scheduling

Accurately estimating the impact of road maintenance schedules on traffic conditions is important because maintenance operations can substantially worsen congestion if not carefully planned. Reliable estimates allow planners to avoid excessive delays during periods of roadwork. Since the exact increase in congestion is difficult to predict analytically, traffic simulations are commonly used to assess the redistribution of the flow of traffic. However, when applied to long-term maintenance planning involving many overlapping projects and scheduling alternatives, these simulations must be run thousands of times, resulting in a significant computational burden. This paper investigates the use of machine learning-based surrogate models to predict network-wide congestion caused by simultaneous road renovations. We frame the problem as a supervised learning task, using one-hot encodings, engineered traffic features, and heuristic approximations. A range of linear, ensemble-based, probabilistic, and neural regression models is evaluated under an online learning framework in which data progressively becomes available. The experimental results show that the Costliest Subset Heuristic provides a reasonable approximation when limited training data is available, and that most regression models fail to outperform it, with the exception of XGBoost, which achieves substantially better accuracy. In overall performance, XGBoost significantly outperforms alternatives in a range of metrics, most strikingly Mean Absolute Percentage Error (MAPE) and Pinball loss, where it achieves a MAPE of 11% and outperforms the next-best model by 20% and 38% respectively. This modeling approach has the potential to reduce the computational burden of large-scale traffic assignment problems in maintenance planning.

cs.LG↗

arXiv2024

Solving Dual Sourcing Problems with Supply Mode Dependent Failure Rates

This paper investigates dual sourcing problems with supply mode dependent failure rates, particularly relevant in managing spare parts for downtime-critical assets. To enhance resilience, businesses increasingly adopt dual sourcing strategies using both conventional and additive manufacturing techniques. This paper explores how these strategies can optimise sourcing by addressing variations in part properties and failure rates. A significant challenge is the distinct failure characteristics of parts produced by these methods, which influence future demand. To tackle this, we propose a new iterative heuristic and several reinforcement learning techniques combined with an endogenous parameterised learning (EPL) approach. This EPL approach - compatible with any learning method - allows a single policy to handle various input parameters for multiple items. In a stylised setting, our best policy achieves an average optimality gap of 0.4%. In a case study within the energy sector, our policies outperform the baseline in 91.1% of instances, yielding average cost savings up to 22.6%.

cs.LG↗

arXiv2023

The Stochastic Dynamic Post-Disaster Inventory Allocation Problem with Trucks and UAVs

Humanitarian logistics operations face increasing difficulties due to rising demands for aid in disaster areas. This paper investigates the dynamic allocation of scarce relief supplies across multiple affected districts over time. It introduces a novel stochastic dynamic post-disaster inventory allocation problem with trucks and unmanned aerial vehicles delivering relief goods under uncertain supply and demand. The relevance of this humanitarian logistics problem lies in the importance of considering the inter-temporal social impact of deliveries. We achieve this by incorporating deprivation costs when allocating scarce supplies. Furthermore, we consider the inherent uncertainties of disaster areas and the potential use of cargo UAVs to enhance operational efficiency. This study proposes two anticipatory solution methods based on approximate dynamic programming, specifically decomposed linear value function approximation and neural network value function approximation to effectively manage uncertainties in the dynamic allocation process. We compare DL-VFA and NN-VFA with various state-of-the-art methods (exact re-optimization, PPO) and results show a 6-8% improvement compared to the best benchmarks. NN-VFA provides the best performance and captures nonlinearities in the problem, whereas DL-VFA shows excellent scalability against a minor performance loss. The experiments reveal that consideration of deprivation costs results in improved allocation of scarce supplies both across affected districts and over time. Finally, results show that deploying UAVs can play a crucial role in the allocation of relief goods, especially in the first stages after a disaster. The use of UAVs reduces transportation- and deprivation costs together by 16-20% and reduces maximum deprivation times by 19-40%, while maintaining similar levels of demand coverage, showcasing efficient and effective operations.

math.OC↗

arXiv2023

Learning Dynamic Selection and Pricing of Out-of-Home Deliveries

Home delivery failures, traffic congestion, and relatively large handling times have a negative impact on the profitability of last-mile logistics. A potential solution is the delivery to parcel lockers or parcel shops, denoted by out-of-home (OOH) delivery. In the academic literature, models for OOH delivery were so far limited to static settings, contrasting with the sequential nature of the problem. We model the sequential decision-making problem of which OOH location to offer against what incentive for each incoming customer, taking into account future customer arrivals and choices. We propose Dynamic Selection and Pricing of OOH (DSPO), an algorithmic pipeline that uses a novel spatial-temporal state encoding as input to a convolutional neural network. We demonstrate the performance of our method by benchmarking it against two state-of-the-art approaches. Our extensive numerical study, guided by real-world data, reveals that DSPO can save 19.9%pt in costs compared to a situation without OOH locations, 7%pt compared to a static selection and pricing policy, and 3.8%pt compared to a state-of-the-art demand management benchmark. We provide comprehensive insights into the complex interplay between OOH delivery dynamics and customer behavior influenced by pricing strategies. The implications of our findings suggest practitioners to adopt dynamic selection and pricing policies.

cs.LG↗

arXiv2021

A Markov Decision Process Approach for Managing Medical Drone Deliveries

We consider the problem of optimizing the distribution operations at a drone hub that dispatches drones to different geographic locations generating stochastic demands for medical supplies. Drone delivery is an innovative method that introduces many benefits, such as low-contact delivery, thereby reducing the spread of pandemic and vaccine-preventable diseases. While we focus on medical supply delivery for this work, drone delivery is suitable for many other items, including food, postal parcels, and e-commerce. In this paper, our goal is to address drone delivery challenges related to the stochastic demands of different geographic locations. We consider different classes of demand related to geographic locations that require different flight ranges, which is directly related to the amount of charge held in a drone battery. We classify the stochastic demands based on their distance from the drone hub, use a Markov decision process to model the problem, and perform computational tests using realistic data representing a prominent drone delivery company. We solve the problem using a reinforcement learning method and show its high performance compared with the exact solution found using dynamic programming. Finally, we analyze the results and provide insights for managing the drone hub operations.

math.OC↗