How To Fix RSDME235 - Some model fields had untrained values; hence are treated as missing

SAP Error Message - Details

• Message type: E = Error

• Message class: RSDME -

• Message number: 235

• Message text: Some model fields had untrained values; hence are treated as missing

What causes this issue?

Some model fields had values not found during the training. Prediction
was performed by treating such values as missing.
Choose <LS>Show Message</> to view which model fields were affected.

The system issues an error message and will not allow you to continue with this transaction until the error is resolved.

System Response

How to fix this error?

Ignore this message if the given values were intentional. Otherwise,
use the possible entries function (F4 help) to choose the valid value.

Procedure for System Administrators

Error message extract from SAP system. Copyright SAP SE.

Smart SAP Assistant

• What is the cause and solution for SAP error message RSDME235 - Some model fields had untrained values; hence are treated as missing ?

  The SAP error message RSDME235 indicates that some fields in a model (typically in SAP BW or SAP HANA) contain values that have not been trained or recognized by the model. This often occurs in the context of predictive analytics or machine learning models where certain input values do not match the expected or trained values.
  Cause:
  
  Untrained Values: The model has not been trained on certain values present in the dataset. This can happen if new categories or values are introduced after the model was trained.
  Data Quality Issues: There may be inconsistencies or errors in the data, such as typos, incorrect formats, or missing values.
  Changes in Data Schema: If the underlying data structure has changed (e.g., new fields added, existing fields modified), the model may not recognize the new or altered values.
  Insufficient Training Data: The model may not have been trained on a sufficiently diverse dataset, leading to gaps in its ability to handle certain values.
  
  Solution:
  
  Re-train the Model: Update the model by re-training it with a more comprehensive dataset that includes the untrained values. This will help the model learn to recognize and handle these values.
  Data Preprocessing: Clean and preprocess the data to ensure that it is consistent and free of errors. This may involve standardizing formats, correcting typos, and handling missing values appropriately.
  Check Data Mapping: Ensure that the data being fed into the model matches the expected schema and that all necessary fields are included.
  Use Default Values: If certain values are not critical, consider using default values or imputation techniques to handle missing data.
  Model Evaluation: Regularly evaluate the model's performance and update it as necessary to ensure it remains accurate and effective.
  
  Related Information:
  
  Documentation: Refer to SAP's official documentation for guidance on model training and data preparation.
  SAP Community: Engage with the SAP Community forums for insights and solutions from other users who may have encountered similar issues.
  Error Logs: Check the error logs for additional context or details that may help in diagnosing the issue.
  Version Updates: Ensure that you are using the latest version of SAP software, as updates may include bug fixes and improvements related to model training and data handling.
  
  By addressing the underlying causes and implementing the suggested solutions, you can resolve the RSDME235 error and improve the performance of your SAP models.