CoolFace
Apppublic

GIZ/Development-Project-Synergy-Finder

sourceHugging Facemitupdated 4mo agoView on Hugging Face
2likes
README.md86 linesDownload Raw Back to root
1---2title: Development Project Synergy Finder3python_version: 3.114emoji: 🌍5colorFrom: pink6colorTo: gray7sdk: streamlit8sdk_version: 1.32.29app_file: app.py10pinned: true11short_description: Discover Development Organization's Projects12license: mit13---14 15Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference16 17# Technical Documentation of the system in accordance with EU AI Act.18 19 20## System Name: Development Project Synergy Finder21 22Provider / Supplier: GIZ Data Service Center23 24As of: July 202525 26 27### General Description of the System28 29Multiple international organizations have projects in the same field and region. These projects could collaborate or learn from 30each other to increase their impact if they were aware of one another. The Project Synergy Finder facilitates the search for 31similar projects across different development organizations and banks. Note that this app is a prototype, results may be 32incomplete or inaccurate.33 34### Models35 36**SDG Text Classifier**37 38Model Name: bert-base-uncased-finetuned-sdg (link will follow soon, if you have questions please contact us at dataservicecenter@giz.de)39Base Model: [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased)40Usage: The SDG categorization in this tool is AI-predicted based on project descriptions and titles using a SDG Classifier trainded on the OSDG dataset.41License: apache-2.042Model Training Data: The training data has been collected by human annotators that are expert in their fields. If you have questions regarding the dataset, please 43reach out to dataservicecenter@giz.de. 44Bias: The data does not contain any known bias, however risk of potential bias can never be fully excluded.45 46### Data47 48**IATI Data**: The data is sourced from the IATI d-portal, providing project-level information. The International Aid Transparency Initiative (IATI) aims 49to enhance transparency and effectiveness in development cooperation by making data publicly accessible.50Data Update: The data is updated irregularly, with the last retrieval on 10th May 2024.51Project Data: Data from projects labeled as active during the last data retrieval are included. The data includes Project Title, Description, URL, Country, and Sector classification (CRS). The CRS5 and CRS3 classifications organize development cooperation into categories, with the 5-digit level providing more specific details within the broader 3-digit categories.52 53**Organizations**: The tool currently includes projects from the following organizations:54 55- IAD: Inter-American Development Bank56- ADB: Asian Development Bank57- AfDB: African Development Bank58- EIB: European Investment Bank59- WB: World Bank60- WBTF: World Bank Trust Fund61- BMZ: Federal Ministry for Economic Cooperation and Development (Germany)62- KfW: KfW Development Bank (Germany)63- GIZ: Deutsche Gesellschaft für Internationale Zusammenarbeit (Germany)64- AA: German Federal Foreign Office (Germany)65 66**Additional Data:** The Sustainable Development Goals (SDGs) are 17 UN goals aimed at achieving global sustainability, peace, and prosperity by 2030.67The SDG categorization in this tool is AI-predicted based on project descriptions and titles using a SDG Classifier trainded on the OSDG dataset.68 69 70### System Usage71 72The system is a prototype designed to facilitate the quick search of similar projects across different development organizations. 73The system is NOT designed to give a complete overview of all ongoing projects and their matching counterparts. Output may always be incomplete or falsly 74classified and should ALWAYS be reviewed by a human.75The system does not make autonomous decisions but just provides information.76No personal data of users is being processed.77Results are intended for orientation only – not for legal or political advice.78 79### Transparency Towards Users80The user interface clearly indicates the use of a fine-tuned text classification transformer models and outlines that the system is a prototype.81 82 83### Contact & Feedback 84Technical development is carried out by the GIZ Data Service Center.85Please reach out through the contact details provided below, if there are any issues or feedback.86Contact: For any questions, please contact us via dataservicecenter@giz.de