# Limitation of Credit Score

The reliability and validity of the credit scoring model are contingent upon a thorough understanding of its limitations. At FiinGroup, we understand that no scoring model is perfect and that its output is only as good as the input that goes into it. This is why it is essential for our management to be aware of the potential limitations of our FiinGroup CreditScore.

* **Data accuracy**: One limitation is that the scoring model output is only as good as the input that is used. If data going into the scoring model is inaccurate or delayed, the model’s output (score) will be erroneous.
* **Model Reliability**: a model has good risk ranking an overall market segment, can be limited if they do not reflect the population. In case of a score small or some specific sample with unique characteristics, a model may not perform as tested.
* **Information limitation**: a company may default because of unknown reasons or information not available.
* **Shock Economic events**: Along similar lines, during times of strong economic growth, models may be ill-prepared to predict borrower performance in some recessionary conditions, particularly if the historic period observed did not include recessionary conditions.
* **Human Involvement**: Another limitation of the credit scoring model is the potential for human involvement to compromise its results. For example, when models are augmented by managerial judgment (for instance, in the case of overrides), results from the model and subsequent validation processes can become seriously compromised.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.fiingate.vn/manual/methodology/credit-scoring-models/limitation-of-credit-score.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
