To wrap up, let’s use the model to make a prediction.
We’re going to invent a fake housing block in San Francisco, in the middle of the Mission district. The block has 2500 rooms, 1000 bedrooms, houses 500 people and 150 households. The apartments are 10 years old on average, and the normalized median income in that neighborhood is 2.0.
For how much could you sell an apartment in that housing block?
We will ask our AI agent to write code that prompts us for all the properties of a single housing block, and then we’ll use the machine learning model to predict what the median house value will be for any apartment in the block.
...
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