I am planning to leverage Lumenore Ask Me for the analytics and would like to ensure that my dataset is properly structured to achieve a high AI Score and deliver accurate, context-aware responses.

My dataset contains transactional data such as:

• Date fields
• Categorical dimensions (Region, Product, Category, etc.)
• Business metrics (Sales, Revenue, Quantity, etc.)

In addition to making the dataset NLQ-ready, I would like guidance on how to further optimize it so that Lumenore AI can better understand user intent and provide more precise answers.

Specifically, I would like to understand:

• What modeling best practices improve AI Score in Lumenore Ask Me?
• Are there recommended naming conventions or business-friendly labels that enhance NLP interpretation?
• How should measures, calculated fields, and date hierarchies be structured for better AI understanding?
• Does adding descriptions, synonyms, or metadata improve AI performance?
• What common data preparation mistakes negatively impact AI Score?

My objective is to enable business users to ask questions such as:

• “Show sales by region for 2023”
• “What is the YOY growth in revenue?”
• “Top 5 products by sales last quarter”

I would appreciate any best practices or recommendations to align my dataset with Lumenore Ask Me interpretation model and improve both AI Score and response accuracy.