Customer Experience

Customer experience (CX) data tracks investments and efforts aimed at improving customer interactions, satisfaction, and loyalty. The primary focus is on monetary investments (e.g., in IT infrastructure, human resources, training, or other initiatives) to enable ROI estimation through modeling. This data helps quantify how CX enhancements contribute to business outcomes like retention, sales uplift, or KPI improvements.

CX metrics (e.g., Net Promoter Score (NPS), Voice of Customer (VOC), satisfaction scores) should be included in the Brand file instead, as they represent outcomes rather than inputs. Sourced from internal financial records, project budgets, or CRM systems, this data allows Alviss AI to incorporate CX investments as drivers in attributions, simulations, predictions, and optimizations. For example, it can model the impact of investing in customer support teams on overall revenue.

Data Requirements

The Customer Experience 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 investment occurred.
• 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 date of the investment in ISO 8601 format (YYYY-MM-DD).
• Product (string, required): The name or identifier of the product or service associated with the investment (e.g., "Brand", "Pc", "Life").
• Channel (string, required): The type of CX activity or initiative (e.g., "IT" for technology investments, "Human" for staffing or training, "Non Human" for automated systems).
• Investment (float, required): The investment amount in local currency (e.g., 107204). Use a period (.) as the decimal separator. Handle missing or zero values explicitly—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 investment per product, channel, date, etc.).

• Wide Format (Useful for spreadsheets): Columns represent combinations of Product and Channel, 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.
• Channel Definition: Use consistent and descriptive channel names (e.g., "IT", "Human", "Non Human") to reflect investment types. This aids in modeling different CX levers.

Common Issues and Troubleshooting

• Metrics vs. Investments: Avoid including outcome metrics here—route them to Brand to prevent model confusion.
• Differentiation from Other Investments: Ensure CX data is uploaded separately from media or other spends to maintain clear modeling distinctions.

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