Abstract
This study reflects the assumption that all links in a supply chain (SC) must share responsibility for socio-environmental issues. One of the main barriers to ensuring the sustainability of an SC is the difficulty in accessing partners' information, especially beyond the first tier. Due to the great geographical dispersion, large number of small companies, and, mainly, the growth of the fast fashion industry, the textile sector is recognised as a priority when it comes to social sustainability issues. Moreover, consumers are increasingly demanding information about the social footprint of products. Thus, this paper aims to contribute to a better understanding of how SC visibility can contribute to increasing the social sustainability of textile SCs. Using a longitudinal perspective and adopting mixed methods integrated into a design science strategy, we evaluate SC visibility in the context of two Portuguese textile supply chains, before and after the development of a technology-based solution.

Abstract

Abstract

Abstract
The Circular Economy, an alternative to the linear make-use-dispose system, promotes sustainable development through novel business models. Thus, Circular Business Models emerge as systems that minimize resource input and waste by slowing, closing, and narrowing material and energy loops. Circular Startups play a crucial role in the transition to a Circular Economy. Despite their significance, there is a research gap in how these companies scale. Moreover, the slow transition is attributed to the limited scalability of Circular Business Models, which leads to the need to scale current practices. The present study aims to fill this gap by defining a typology of scalability strategies employed by circular startups. A qualitative case studies methodology is adopted, using document analysis and semi-structured interviews conducted in the context of the European project SoTecIn Factory. This research identifies five scalability strategies used by Circular Startups-impact, commercial, ecosystem, institutional and cultural-with the commercial strategy being the main focus in terms of growth approach. The findings underline a strong commitment across the observed value chains to minimize environmental impact, enhance social welfare, and foster economic growth. Other key findings reveal the presence of R-imperatives across different value chains, leading to industry-specific approaches. In addition to the theoretical contribution, this research can support sustainable growth by practitioners in their scaling efforts, thus, accelerating the circular transformation. © 2025 The Authors.

Abstract

Abstract
Traffic flow prediction is a critical component of intelligent transportation systems. This study introduces a Bidirectional Long Short-Term Memory (Bi-LSTM) neural network for predicting traffic flow. The model utilizes traffic, weather, and holiday data. To evaluate the model's performance, three experiments were assessed: E1, using all available inputs; E2, excluding weather conditions; and E3 excluding holiday information. The model was trained using the previous 3, 12, and 24 h of data to predict traffic flow for the next 12 h, and its performance was compared with a LSTM model. Traffic predictions benefit from having a large and diverse dataset. Bi-LSTM model can capture temporal patterns more effectively than the LSTM. The MAPE value is improved in around 1% when we increase the historical from 3h to 24 h, plus 1% if Bi-LSTM model is used. Better results are obtained when contextual information is provided. These results reinforce the potential that deep learning models have in the prediction of traffic conditions and the impact of a large and varied dataset in the accuracy of these predictions.