A low bias and high variance problem is overfitting. Different data sets are depicting insights given their respective dataset. Hence, the models will predict differently. However, if average the results, we will have a pretty accurate prediction.
The predictions will be similar to one another but on average, they are inaccurate.
Source: https://becominghuman.ai/machine-learning-bias-vs-variance-641f924e6c57
https://www.youtube.com/watch?v=EuBBz3bI-aA
Information about predictions that are based on possibly biased data are clearly communicated to the urban planner. He can then inspect the potentially problematic areas.
Immediate suggestions inspire the urban planner to take action within the problematic area. Multiple possible actions tackle different aspects of the problem.
The agent presents fitting methods for tackling the problem, enabling the urban planner to incorporate these into the planning process.
In order to better understand the agent's concerns, the urban planner can view the reasoning for why the agent believes there is a problem.