Abstract
The emergence of Industry 4.0 is making production systems more flexible and also more dynamic. In these settings, schedules often need to be adapted in real-time by dispatching rules. Although substantial progress was made until the '90s, the performance of these rules is still rather limited. The machine learning literature is developing a variety of methods to improve them. However, the resulting rules are difficult to interpret and do not generalise well for a wide range of settings. This paper is the first major attempt at combining machine learning with domain problem reasoning for scheduling. The idea consists of using the insights obtained with the latter to guide the empirical search of the former. We hypothesise that this guided empirical learning process should result in effective and interpretable dispatching rules that generalise well to different scenarios. We test our approach in the classical dynamic job shop scheduling problem minimising tardiness, one of the most well-studied scheduling problems. The simulation experiments include a wide spectrum of scenarios for the first time, from highly loose to tight due dates and from low utilisation conditions to severely congested shops. Nonetheless, results show that our approach can find new state-of-the-art rules, which significantly outperform the existing literature in the vast majority of settings. Overall, the average improvement over the best combination of benchmark rules is 19%. Moreover, the rules are compact, interpretable, and generalise well to extreme, unseen scenarios. Therefore, we believe that this methodology could be a new paradigm for applying machine learning to dynamic optimisation problems.

Abstract
In this paper, we explore the value of considering simultaneous pickups and deliveries inmulti-product inventory-routing problems both with deterministic and uncertain demand. Wepropose a multi-commodity, develop an exact branch-and-cut algorithm with patching heuristicsto efficiently tackle this problem, and provide insightful analyses based on optimal plans. Thesimplicity of the proposed approach is an important aspect, as it facilitates its usage in practice,opposed to complicated stochastic or probabilistic methods. The computational experimentssuggest that in the deterministic demand setting, pickups are mainly used to balance initialinventories, achieving an average total cost reduction of 1.1%, while transshipping 2.4% oftotal demand. Under uncertain demand, pickups are used extensively, achieving cost savings of up to 6.5% in specific settings. Overall, our sensitivity analysis shows that high inventory costsand high degrees of demand uncertainty drive the usage of pickups, which, counter-intuitively, are not desirable in every case

Abstract
The Minimum Life on Receipt (MLOR) is a widely used rule that imposes the minimum remaining age a food product must be delivered by the producer to the retailer. In practice, this rule is set by retailers and it is fixed, around 2/3 of the age of products regardless their shelf life. In this work, we study single and two echelon make-to-stock production-inventory problems for fixed-lifetime perishables. Mixed-integer linear optimization models are developed considering the MLOR rule both as decision variable and fixed parameter. When the MLOR rule is a variable, it is considered either a sole decision of the producer or a collaborative decision between retailer and producer. The goal of this work is to compare the supply chain performance considering this innovative setting of optimal MLOR (as a variable) against the traditional setting of fixed MLOR rule. The computational results suggest that allowing flexible MLOR rules according to the shelf life of products and the operational requirements of the producer benefit both entities in the supply chain. In particular, reducing the MLOR requirement in up to 12% does not interfere substantially with the average freshness of products arriving to the retailer, but reduces extensively surplus/waste generation at the producer while keeping a small amount of waste at the retailer.

Abstract
This paper addresses the impact of consumer purchasing behaviour on the production planning of perishable food products for companies operating in the fast moving consumer goods using direct store delivery. The research presented here builds on previous marketing studies related to the effects of expiry dates in order to derive mathematical formulae, which express the age dependent demand for different categories of perishable products. These demand expressions take into account both customer willingness to pay and product quality risk. The paper presents deterministic and stochastic production planning models, which incorporate the customer's eagerness to pick up the fresher products available. Results indicate that model approximations neglecting the fact that customers pick up the fresher products or considering that all products have the same product quality risk have a reduced impact on profit losses. On the other hand, not considering the decreasing customer willingness to pay has an important impact both on the profit losses and on the amount of spoiled products.

Abstract
This paper presents a successful application of operations research techniques in guiding the decision making process to achieve a superior operational efficiency in core activities. We focus on a rich vehicle routing problem faced by a Portuguese food distribution company on a daily basis. This problem can be described as a heterogeneous fleet site dependent vehicle routing problem with multiple time windows. We use the adaptative large neighbourhood search framework, which has proven to be effective to solve a variety of different vehicle routing problems. Our plans are compared against those of the company and the impact that the proposed decision support tool may have in terms of cost savings is shown. The algorithm converges quickly giving the planner considerably more time to focus on value-added tasks, rather than manually correct the routing schedule. Moreover, contrarily to the necessary adaptation time of the planner, the tool is quite flexible in following market changes, such as the introduction of new customers or new products.

Abstract
This paper explores robust unconditional and conditional nonparametric approaches to support performance evaluation in problematic samples. Real-world assessments often face critical problems regarding available data, as samples may be relatively small, with high variability in the magnitude of the observed indicators and contextual conditions. This paper explores the possibility of mitigating the impact of potential outlier observations and variability in small samples using a robust nonparametric approach. This approach has the advantage of avoiding unnecessary loss of relevant information, retaining all the decision-making units of the original sample. We devote particular attention to identifying peers and targets in the robust nonparametric approach to guide improvements for underperforming units. The results are compared with a traditional deterministic approach to highlight the proposed method's benefits for problematic samples. This framework's applicability in internal benchmarking studies is illustrated with a case study within the wastewater treatment industry in Portugal.