Extra

Extra data encompasses any additional variables or metrics that do not fit neatly into other predefined categories (e.g., brand, media, sales). This flexible file type allows you to include custom indicators such as agreements, supply chain performance, inquiries, or other business-specific data points that may influence your models.

Sourced from internal systems, external reports, or custom trackers, this data enables Alviss AI to incorporate unique drivers into attributions, simulations, predictions, and optimizations. For example, it can model how supply chain disruptions or inquiry volumes affect sales, providing a way to capture niche factors for more tailored insights. Use this category sparingly—prioritize fitting data into standard types when possible to maintain consistency.

Data Requirements

The Extra Data file must include the following columns (headers). All columns are required unless marked as optional:

• Country (string, required): A three-letter country code per ISO 3166 standard (e.g., "SWE" for Sweden), indicating where the indicators were collected.
• Region (string, required): The region within the country (e.g., "all" for nationwide or a specific ISO 3166-2 code like "SE-AB" for Stockholm County in Sweden).
• Grouping (string, optional): For additional segmentation, such as product categories, demographics, or sales territories (e.g., "all" if not applicable).
• Date (date, required): The collection date in ISO 8601 format (YYYY-MM-DD).
• Variable (string, required): The name or identifier of the custom variable (e.g., "Agreements", "SupplyChain", "Inquiries").
• Value (float, required): The value of the variable (e.g., 21.33). Use consistent units; handle missing values with NaN or blanks—Alviss AI will flag inconsistencies during upload.

Supported Formats

Data can be uploaded in long (tidy) or wide (pivoted) format. Choose based on your data pipeline:

• Long Format (Recommended for flexibility): Each row represents a single observation (one value per variable, date, etc.).

• Wide Format (Useful for spreadsheets): Columns represent different variables, with rows as dates. The first few rows define fixed attributes (e.g., Country, Region).

Best Practices

• Consistency: Ensure dates align with your project's periodicity (e.g., weekly data if the project is set to weekly granularity). Mismatched granularity will cause upload errors.
• Data Quality: Check for outliers, missing values, or inconsistencies before upload. Use the Activities dashboard to visualize and validate post-upload.
• Granularity Alignment: All data in a project must match the chosen periodicity (set during project creation). For details, see Projects.
• Variable Naming: Use clear, descriptive names for variables to facilitate model interpretation and filtering. Avoid duplicates with standard categories.

For uploading instructions, see Upload Data. If you encounter issues, contact support or refer to the API for programmatic uploads.