The growing focus on environmental sustainability has driven industries to adopt Life Cycle Assessment (LCA) to quantify environmental impacts. However, in the furniture sector, challenges arise due to the emphasis on craftsmanship, quality materials, and customization, making complex assessments difficult for small and medium enterprises. This research presents an integrated eco-design framework tailored to the furniture sector, which utilizes machine learning algorithms to support sustainable decision-making from early design stages. The framework introduces three key tools: a Qualitative Feedback Tool for gathering stakeholder input, an Eco-Design Tool for developing guidelines through machine learning, and a Simplified LCA Tool for conducting rapid environmental assessments. A case study with a leading furniture company validates the approach, focusing on the development of a sustainable seating archetype. Results show that the framework enhances decision-making efficiency, embeds sustainability early in the design process, and reduces costly late-stage modifications. By merging machine learning with eco-design, the study provides a structured and accessible path to sustainable product development, emphasizing the importance of integrating sustainability as a core design principle rather than an external constraint. This methodology offers valuable support for companies aligning with environmental regulations and meeting the growing demand for sustainable products.