What information are more relevant for the predicted results?
Within this section, you will encounter the best explainable visualisations to discern the relevant information crucial for predictions. The primary focus here is to assist in post-prediction analysis, aiding you in comprehending the significance of various factors once a prediction has been generated.
<span data-metadata=""><span data-buffer="">Text Plot<span data-metadata="">
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.
