Report
💡 Active projects and challenges as of 28.02.2026 00:56.
Full text CSV Data Package Print
Guest
NeuroBin: Smart Waste Segregator
NeuroBin is an Edge-AI powered smart waste segregator that automatically sorts waste into biodegradable (food scraps, paper, garden waste) and non-biodegradable (plastics, metals, packaging) categories using a CNN model on Raspberry Pi 4.It integrates HC-SR04 ultrasonic sensors for object detection, MG90S servo motors for precise sorting, and achieves ~12 items/min throughput with <500ms latency, reducing manual sorting and contamination.Targeting UN SDG 11, NeuroBin cuts municipal overflow costs with scalable hardware sales (₹35–45K/unit, 65–70% margin) and SaaS analytics for waste insights.
FundingNavigator – Smart Matching for Social Funding in Switzerland
Social workers and individuals in financial distress spend hours manually searching through PDF directories to find the right foundation for their specific situation – only to face rejection because the foundation's purpose didn't match their case. The ZHAW "Fonds und Stiftungsverzeichnis" alone lists 188 foundations for the Canton of Zurich, each with specific eligibility criteria regarding target group, nationality, residency, type of need, and application process. Mismatched applications waste time for both applicants and foundations, which report being overwhelmed by unsuitable requests. FundingNavigator turns this static knowledge into an intelligent matching tool. Users answer a guided set of questions – Who are you? (individual, social worker, organization) What do you need? (emergency funds, education, project grant) How urgent is it? – and the system matches them to the most suitable funding sources. But we go beyond classical foundation directories: FundingNavigator integrates the full spectrum of social financing options, including crowdfunding platforms, sharing economy resources, and public support programs, following the holistic approach of the ZHAW directory. The prototype could use a RAG-based architecture (Retrieval-Augmented Generation) with the structured foundation data as its knowledge base. Core features for the hackathon: (1) guided needs assessment, (2) intelligent matching with ranked results, (3) urgency-based filtering (decision timelines vary from weeks to months), (4) direct links to application forms or auto-generated template letters. The architecture is designed to scale beyond Zurich to other cantons and national-level foundations. Data source: ZHAW Fonds- und Stiftungsverzeichnis 2024/25 (publicly available, 188 foundations + supplementary financing chapters). Impact: Fewer mismatched applications, faster access to support for people in crisis, reduced administrative burden on foundations, and a scalable model for all of Switzerland.
Guest
EmSol barrier killer
The Fondation Emploi Solidarité is active in the field of professional reintegration and the circular economy. We receive donations in kind from the population of the canton of Fribourg, which we revalue in our various ateliers and then sell in our four second-hand boutiques. This enables us to finance around 60% of our work ourselves, with the remainder being financed through service contracts with the public sector. We plan to offer certified training courses in various areas of our activity (cashier/sales, e-commerce, recycling, refurbishment, etc.) to enable our participants to increase their chances of reintegration by obtaining a training certificate. This will supplement the practical training they receive in our workshops and boutiques with training on aspects that they cannot see at our premises and with theoretical basics. As our target audience tends to be people with little education and few qualifications, and our employees are not trainers but work coaches, we want to use AI tools to develop audio-visual teaching materials that are tailored to the needs and level of our target audience. In addition, we would like to train our target audience in the use of AI tools that enable them to overcome existing barriers (linguistic, health and other) and thus participate fully in the programme and also use these tools in their work in the economy and in their private lives, thereby increasing their social participation. Here, too, we want to use AI to develop the appropriate teaching materials and find the most suitable AI tools to make our participants' everyday lives easier. We therefore hope that Hack4SocialGoods will provide us with specialists who can help us find the most suitable AI tools for creating teaching materials and coping with everyday (working) life, and prepare for implementation, which should ideally be done in a participatory manner with the involvement of the team. Our main client has currently put all investments on hold, so we cry to find no cost / low-cost-solutions
Guest
L'Intelligence comme chance de participation non comme risque
The Fondation Emploi Solidarité is active in the field of professional reintegration and the circular economy. We receive donations in kind from the population of the canton of Fribourg, which we revalue in our various ateliers and then sell in our four second-hand boutiques. This enables us to finance around 60% of our work ourselves, with the remainder being financed through service contracts with the public sector. We plan to offer certified training courses in various areas of our activity (cashier/sales, e-commerce, recycling, refurbishment, etc.) to enable our participants to increase their chances of reintegration by obtaining a training certificate. This will supplement the practical training they receive in our workshops and boutiques with training on aspects that they cannot see at our premises and with theoretical basics. As our target audience tends to be people with little education and few qualifications, and our employees are not trainers but work coaches, we want to use AI tools to develop audio-visual teaching materials that are tailored to the needs and level of our target audience. In addition, we would like to train our target audience in the use of AI tools that enable them to overcome existing barriers (linguistic, health and other) and thus participate fully in the programme and also use these tools in their work in the economy and in their private lives, thereby increasing their social participation. Here, too, we want to use AI to develop the appropriate teaching materials and find the most suitable AI tools to make our participants' everyday lives easier. We therefore hope that Hack4SocialGoods will provide us with specialists who can help us find the most suitable AI tools for creating teaching materials and coping with everyday (working) life, and prepare for implementation, which should ideally be done in a participatory manner with the involvement of the team. Our main client has currently put all investments on hold, so we cry to find no cost / low-cost-solutions
Guest
Modèle participatif de gouvernance pour la primo-information
Les informations utiles à l’intégration sont produites par une grande diversité d’acteurs (institutions publiques, associations, services sociaux, organismes de formation). Cette multiplicité rend difficile la mise à jour, la fiabilité et la traçabilité des contenus, ce qui limite leur utilisation par les bénéficiaires et les professionnels. Ce défi propose de concevoir un prototype de système de gouvernance collaborative permettant de structurer la production, la validation et l’actualisation des informations d’intégration. Vous explorerez la création de workflows multi-acteurs, de mécanismes de validation, de systèmes de traçabilité des sources et d’indicateurs de fiabilité des contenus. Le projet pourra inclure des outils facilitant la contribution des acteurs de terrain, la détection automatique d’informations obsolètes et la visualisation des réseaux d’acteurs impliqués. L’objectif est de proposer un modèle reproductible permettant d’assurer la qualité, la pérennité et la transparence des contenus diffusés via une plateforme d’intégration.
Guest
Moteur intelligent d’orientation personnalisée pour les primo-arrivants
Les migrants nouvellement arrivés sont confrontés à une grande quantité d’informations fragmentées, souvent difficiles à relier à leur situation personnelle. Cette complexité peut ralentir leur intégration et rendre l’accompagnement plus difficile pour les professionnels du terrain. Ce défi consiste à concevoir un prototype de moteur d’orientation personnalisée capable d’analyser le profil et les besoins d’un utilisateur afin de recommander des parcours d’intégration adaptés. Le système devra prendre en compte plusieurs dimensions telles que la langue, le niveau de formation, la situation administrative, l’expérience professionnelle ou les objectifs d’intégration. Le hackathon explorera différentes approches technologiques, comme des modèles de recommandation explicables, des arbres décisionnels interactifs ou des assistants conversationnels. Une attention particulière sera portée à la transparence des recommandations et à l’accessibilité pour des publics à faible littératie numérique. L’objectif est de démontrer comment un outil numérique peut faciliter l’autonomisation des bénéficiaires et soutenir le travail des professionnels.
Guest
Plateforme de mentoring professionnel senior
Créer une plateforme en Suisse permettant aux personnes retraitées expérimentées de proposer des prestations de conseil, mentorat ou accompagnement à des entrepreneurs, dirigeants ou particuliers en transition professionnelle. L’objectif est double : valoriser un capital d’expérience encore actif et générer un revenu complémentaire dans un cadre professionnel structuré. Fonctionnalité Création de profils experts Système de matching selon compétences & besoins Réservation & paiement en ligne Visioconférence & suivi Gestion administrative (facturation, contrats, aspects déclaratifs) Autre?
Guest
Transformation multilingue et en français accessible de l’information existante
Les informations liées à l’intégration socioprofessionnelle sont majoritairement diffusées dans un langage administratif complexe, difficilement accessible aux publics migrants, en particulier aux personnes étrangères ou avec une faible habitude du numérique. Ce défi propose de concevoir un prototype permettant de transformer automatiquement des contenus institutionnels en informations compréhensibles, traduites et adaptées culturellement. Le sujet vise à développer un pipeline capable de simplifier des contenus en français facile à lire et à comprendre (FALC), de les traduire dans plusieurs langues courantes du canton — y compris des langues non latines — et de proposer des formats alternatifs (audio, visuel, pictogrammes). Le défi inclut également l’intégration de mécanismes de validation par des acteurs de terrain (interpètes, associations, professionnels). L’objectif est de démontrer comment des technologies d’intelligence artificielle et des approches participatives peuvent améliorer l’accessibilité réelle de l’information et réduire les barrières linguistiques rencontrées par les primo-arrivants.