Electricity expense management presents significant challenges, as this resource is susceptible to various influencing factors. In universities, the demand for this resource is rapidly growing with institutional expansion and has a significant environmental impact. In this study, the machine learning models long short-term memory (LSTM), random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGBoost) were trained with historical consumption data from the Federal Institute of Paraná (IFPR) over the last seven years and climatic variables to forecast electricity consumption 12 months ahead. Datasets from two campuses were adopted. To improve model performance, feature selection was performed using Shapley additive explanations (SHAP), and hyperparameter optimization was carried out using genetic algorithm (GA) and particle swarm optimization (PSO). The results indicate that the proposed cooperative ensemble learning approach named Weaker Separator Booster (WSB) exhibited the best performance for datasets. Specifically, it achieved an sMAPE of 13.90% and MAE of 1990.87 kWh for the IFPR–Palmas Campus and an sMAPE of 18.72% and MAE of 465.02 kWh for the Coronel Vivida Campus. The SHAP analysis revealed distinct feature importance patterns across the two IFPR campuses. A commonality that emerged was the strong influence of lagged time-series values and a minimal influence of climatic variables.

Facing the new challenges in production processes, companies should adopt lean and green practices in product development. In SMEs, the application of these practices is more complex. This work explores the maturity of lean–green methodologies in the product development process in Brazilian and Japanese SMEs. The methodology used is multicriteria, combining the analytic hierarchy process (AHP) and TOPSIS 2-tuple method, applied to four Japanese SMEs and four Brazilian SMEs in the metalworking sector. The criteria for evaluating SMEs are company flexibility, difficulties with NPD, innovation, limited resources, and personnel authority high. The TOPSIS method alternatives refer to 18 lean–green enablers. In the AHP method, the prioritisation of criteria between Japanese and Brazilian specialists presented divergences. In the Japanese context, the incidence of innovation is predominant, while in the Brazilian context, the most important is the limited resources. In the TOPSIS 2-tuple method, the results showed a higher level of maturity in lean–green methodologies in Japanese companies than in Brazilian ones. Lean practices are more evolved compared to sustainable practices in both countries. The study also addressed how open innovation adoption may contribute to innovation and NPD practices. Policymakers need to understand the heterogeneity of innovators within SMEs and how they differently innovate, developing distinct internal and external activities.

Purpose: This paper examines the relationship between different manufacturing strategies and Industry 4.0's (I4.0) critical success factors (CSFs) and technology adoption.Design/methodology/approach: For that, the authors surveyed 165 practitioners from different manufacturers. Participants provided information about the levels of product customization and production volume in their companies. They also indicated the adoption level of I4.0 technologies and CSFs. Using multivariate data techniques, the authors identified four clusters of different manufacturing strategies and two readiness levels based on the establishment of I4.0 CSFs. The adoption level of I4.0 technologies was then cross compared among clusters to identify which technologies are more likely to be supported.Findings: The findings indicate that, in low-readiness companies, the adoption level of I4.0 technologies does not significantly differ between manufacturing strategies. However, when companies present a higher I4.0 readiness, the adoption of I4.0 technologies seem to vary according to the existing manufacturing strategy.Originality/value: This study sheds light on the influence that manufacturing strategies may have on the digital transformation of companies, highlighting which strategies are more likely to offer a context to successfully adopt I4.0 technologies. The identification of these relationships helps to define the expectation regarding the company's digital transformation, determining coherent benchmarks and allowing managers to anticipate potential issues.

Agriculture stands as one of the major economic pillars worldwide, with food production contributing significantly to income growth. However, agricultural activities also entail risks associated with uncontrollable factors along the supply chain. To address these challenges, mathematical models have been developed for forecasting crucial variables in managing agribusiness activities. In this context, this article employs a combination of systematic bibliometric analysis and the Latent Dirichlet Allocation (LDA) method, a semi-automated approach. The main objective of this study was to automate the identification of relevant topics and construct a bibliographic portfolio (BP) covering the period 2015–2022, focusing on methodologies used in articles and other bibliometric analyses. The 30 articles included in the BP address issues related to methodologies applied in the temporal analysis of agricultural commodities. These articles were categorized based on the nature of the prediction models used, classified as (i) machine learning (ML), (ii) machine learning and artificial neural networks (ML-NN), (iii) machine learning and ensemble (ML-Ensemble), (iv) machine learning and hybrid (ML-hybrid), and (v) statistical. Regarding the results, the topic that stood out the most was termed "Forecasting Methods Applied to Agribusiness Time Series." The most utilized classes were ML-hybrid (41.95 %) and statistical (29.31 %), followed by ML-NN (14.94 %), ML (9.20 %), and ML-Ensemble (4.60 %) types. The theoretical contribution of this study lies in identifying literary gaps concerning forecasting methods applied to agribusiness, while its practical implication is to identify forecasting methodologies to support decision-making.