This project focuses on enhancing the brand-influencer matching algorithm implemented in the match_brands function in the cloud_functions/functions.py file. The goal is to improve the accuracy and efficiency of the matching process using data from the Firestore database.
To get started with the project, clone the repository and install the necessary dependencies.
The existing brand-influencer matching algorithm is documented in the docs/match_brands_design_document.md file. This document provides a detailed explanation of the algorithm's logic, the steps involved in the matching process, and any underlying assumptions or constraints.
The data structure and schema of the Firestore database, including the fields and relationships relevant to the matching process, are documented in the docs/firestore_data_structure.md file.
The proposed enhancements to the matching algorithm are implemented in the match_brands function in the cloud_functions/functions.py file. The rationale behind these modifications is documented in the docs/match_brands_design_document.md file.
Comprehensive unit tests have been written to validate the functionality and accuracy of the enhanced matching algorithm. These tests are located in the tests/test_match_brands.py file. Information on how to run these tests and interpret the results is provided in the docs/match_brands_api_documentation.md file.
The API documentation, including any changes in the input/output format of the match_brands function, is updated and can be found in the docs/match_brands_api_documentation.md file.
Guidelines and best practices for using the enhanced matching algorithm, including recommendations for setting up influencer and brand profiles to maximize the accuracy of the matching process, are provided in the docs/match_brands_usage_guidelines.md file.
Any potential limitations or edge cases of the algorithm, as well as recommendations for future improvements, are documented in the docs/match_brands_design_document.md file.
We welcome contributions from the community. Please read our contributing guidelines before submitting a pull request.
This project is licensed under the MIT License. See the LICENSE file for details.