How to explain anomalies?
In this section, the best explainable visualisations to identify anomalies are displayed. Anomalies are deviations or irregularities in data patterns that stand out from the expected or normal behavior. This section will help you to suggest how to clarify irregularities and manage them in order to prevent errors, optimize processes, and enhance the overall quality of data-driven decision-making.
Text Plot
Description
Example from XMANAI
A textual representation can be used to facilitate AI model explainability by converting complex model outputs into human-readable text. Techniques like natural language processing and attention mechanisms help highlight key features and decision-making processes, providing concise and interpretable explanations. This promotes transparency and trust in AI systems for effective communication with end-users.
A text-based explaination is used by a XMANAI demonstrator to illustrate how changing the value of a specific feature will change the outcome of the prediction in a what-if scenario forecast. The user can define specific what-if scenario, changing value of some features and the results is visualised with a simple textual example.
