Abstract
Food waste reduction represents a potential opportunity to enhance environmental sustainability. This is especially important in fresh products such as fresh seafood, where waste levels are substantially higher than those of other food products. In this particular case, reducing waste is also vital to meet demand while conserving fisheries. This paper aims to promote more sustainable supply chains by proposing daily fresh fish demand forecasting models that can be used by grocery retailers to align supply and demand, and hence prevent the production of food waste. To accomplish this goal, we explored the potential of different machine learning models, namely Long Short-Term Memory networks, Feedforward neural networks, Support Vector Regression, and Random Forests, as well as a Holt-Winters statistical model. Demand censorship was considered to capture real demand. To validate the proposed methodology, we estimated the demand for fresh fish in a representative store of a large European retailing company used as a case study. The results revealed that the machine learning models provided accurate forecasts in comparison to the baseline models and the statistical model, with the Long Short-Term Memory networks model yielding, in general, the best results in terms of root mean squared error (27.82), mean absolute error (20.63) and mean positive error (17.86). Thus, the implementation of these types of models can thus have a positive impact on the sustainability of fresh fish species and customer satisfaction.

Abstract
Customer segmentation is increasingly needed in a context where customer interests are vital for companies to survive. This study proposes the use of the weighted RFM (Recency, Frequency, Monetary) supported by data mining techniques and the Analytic Hierarchy Process (AHP), to classify the customers according to their lifetime value (CLV). The customer segments obtained can be used to boost marketing strategies, as these segments enable to differentiate the customers. Each segment of customers is described by a set of rules based on the customers’ purchasing patterns. The methodology developed is validated by using a real case study, i.e. a food industry company, whose core business is the production of biscuits. © IEOM Society International.

Abstract
This paper presents an alternative way of making predictions on the effectiveness and efficacy of Renewable Energy (RE) policies using Decision Trees (DT). As a data-driven process for decision-making, the analysis uses the Renewable Energy (RE) target achievement, predicting whether or not a RE target will likely be achieved (efficacy) and to what degree (effectiveness), depending on the different criteria, including geographical context, characterizing concerns, and policy characteristics. The results suggest different criteria that could help policymakers in designing policies with a higher propensity to achieve the desired goal. Using this tool, the policy decision-makers can better test/predict whether the target will be achieved and to what degree. The novelty in the present paper is the application of Machine Learning methods (through the Decision Trees) for energy policy analysis. Machine learning methodologies present an alternative way to pilot RE policies before spending lots of time, money, and other resources. We also find that using Machine Learning techniques underscores the importance of data availability. A general summary for policymakers has been included.

Abstract
Despite being one of the most cost-effective methods, email marketing remains challenging due to the low rate of opened emails and the high percentage of unsubscribed campaigns. Since the sender and the subject line are the only information that the recipient sees at first when receiving an email, the decision to open an email critically depends on these two factors, which should stand out and catch the recipient's attention. Therefore, the motivation behind this study is to support email campaign editors in choosing a subject line based on its potential quality. We propose and compare several models to measure the quality of a subject line, considering its potential to promote the email opening. The subject lines' structure and content are explored together with different machine learning techniques (Random Forest, Decision Trees, Neural Networks, Naive Bayes, Support Vector Machines, and Gradient Boosting). To validate the proposed model, a data set of 140,000 emails' subject lines was used. The results revealed that the models proposed are very promising to support the definition of the email marketing subject lines and show that the combination of data regarding the structure, the content of the subject lines, and senders characteristics leads to more accurate classifications of the potential of the subject line.

Abstract
The concern about sustainability is growing and the Mediterranean diet has been extensively identified as a promising model, with benefits for human and environmental health. This systematic review aims to identify and describe the indicators that have been used to evaluate the sustainability of the Mediterranean diet and the results from their application. A methodology using PRISMA guidelines was followed, and searches were performed in Web of Science, PubMed, Scopus, and GreenFile. A total of 32 studies assessing the sustainability of the Mediterranean diet were identified. Twenty-five of these studies quantified the environmental impact, 7 studies evaluated the nutritional quality, and 12 studies assessed the daily cost of this dietary pattern. A total of 33 distinct indicators were identified, of which 10 were used to assess the environmental dimension (mainly, carbon, water, and ecological footprint), 8 were used to assess the nutritional dimension (mainly Health score and Nutrient Rich Food Index), 1 was used to assess the economic dimension (dietary cost), and 8 used combined indicators. The remaining 6 indicators for the assessment of sociocultural dimension were only identified in 1 study but were not measured. The Mediterranean diet had a lower environmental impact than Western diets and showed a carbon footprint between 0.9 and 6.88 kg CO2/d per capita, a water footprint between 600 and 5280 m(3)/d per capita, and an ecological footprint between 2.8 and 53.42 m(2)/d per capita. With regard to the nutritional dimension, the Mediterranean diet had a high nutritional quality and obtained 122 points on the Health score and ranged between 12.95 and 90.6 points on the Nutrient Rich Food Index. The cost of the Mediterranean diet is similar to other diets and varied between 3.33 and 14.42euro/d per capita. These findings show that no uniformity in assessing the MDiet's sustainability exists. Statement of Significance: Although several articles have presented the Mediterranean diet (MDiet) as a sustainable diet, it is not clear how this sustainability is being assessed by different authors. This systematic literature review aims to fill this gap, by identifying and describing the indicators used to evaluate the sustainability of the MDiet, taking into account the several sustainability dimensions and looking at the results from their application.

Abstract
Electric mobility with all of its advantages has gained momentum during the last decade with increasing utilization by many sectors of the society. However, professional fleets' operators (e.g. taxis) are still conservative in switching to this new mobility paradigm in many parts of the world. In this paper, we empirically evaluate whether electric vehicles together with conventional charging stations could replace current internal combustion engine vehicles for taxi mobility and study the implications for the taxi business. To perform this study, we resort to a detailed mobility dataset of a taxi fleet collected in a mid-sized European city. The results provide a first indication that such transition towards electric mobility is feasible for the vast majority of the vehicles of the fleet and that simple AC chargers at taxi stands could suffice to provide the necessary range autonomy.