We are seeking a skilled developer to create a data classification script that accurately classifies data using the UNSPSC (United Nations Standard Products and Services Code) Taxonomy. The goal is to achieve a classification accuracy of at least 90%.

Project Overview:

Our company receives data from customers, including Supplier/Vendor Names and Item Descriptions. We need to classify these data points according to the UNSPSC Taxonomy. The classification script will analyze the Supplier Name and Item Description to determine the correct UNSPSC category for each line item.

Key Responsibilities:
- Data Analysis: Analyze incoming data that includes Supplier/Vendor Names and Item Descriptions.
- Script Development: Develop a script or algorithm that uses AI/ML models, including but not limited to ChatGPT, to classify each line item according to the UNSPSC Taxonomy.
- Data Sources: Integrate publicly available data sources, such as stock market data or similar repositories, to improve classification accuracy.
- Accuracy Target: Ensure the script achieves at least 90% classification accuracy.
- Testing & Validation: Conduct rigorous testing and validation of the script to confirm its accuracy and efficiency.
- Documentation: Provide clear documentation of the code, methodology, and any datasets used in the development process.

Skills & Qualifications:
- Programming Skills: Proficient in Python or similar programming languages.
- Experience with AI/ML: Hands-on experience with AI/ML models, particularly in text classification or natural language processing (NLP).
- Data Integration: Familiarity with integrating external data sources for enhanced model accuracy.
- Taxonomy Knowledge: Understanding of the UNSPSC Taxonomy is a plus, though not required.
- Attention to Detail: Ability to ensure high accuracy in data classification.
- Problem-Solving: Strong analytical and problem-solving skills.

Deliverables:
- A fully functional script that classifies Supplier/Vendor Names and Item Descriptions according to the UNSPSC Taxonomy.
- Documentation detailing the implementation, data sources, and accuracy metrics.
- Suggestions for further improvements or refinements to achieve and maintain accuracy.