Automatically determining a current value for a home

1. A non-transitory storage device storing a program to cause a computing system having a processor to perform a method for generating a display relating to a named geographic area, the method comprising:

for each of substantially all of the homes in the named geographical area, accessing an estimated current value attributed to the home based on automatically comparing the attributes of the home to attributes of homes recently sold in the named geographic area using each of a plurality of classification trees among a forest of classification trees, each classification tree of the forest classifying a plurality of homes and their recent selling prices based on values for the homes of the plurality of a random subset of home attributes;

with the processor, applying an aggregation function to the accessed estimated current values to obtain an aggregation result; and

causing to be displayed a characterization of the current value of homes in the named geographic area that is based on the aggregation result.

2. The non-transitory storage device of claim 1 wherein the aggregation function is mean.

3. The non-transitory storage device of claim 1 wherein the aggregation function is median.

4. The non-transitory storage device of claim 1 wherein the aggregation function is maximum.

5. The non-transitory storage device of claim 1 , the method further comprising displaying an indication of the magnitude of change from an earlier characterization of the value of homes in the named geographic area to the characterization of the current value of homes in the named geographic area.

6. A non-transitory storage device for storing a program to cause a computing system having a processor to perform a method for displaying a trend in the overall valuation of homes in a named geographical area, the method comprising:

at a first time:

with the processor, training a first model that values houses in the named geographical area based on their attributes, using attributes and selling prices for homes in the named geographical area that sold in a first period ending before the first time, the first model being a first forest of classification trees, the first forest comprising a plurality of classification trees, each classification tree of the first forest classifying a plurality of homes and their recent selling prices based on values for the homes of the plurality of a random subset of home attributes;

for each of substantially all of the homes in the named geographical area, applying a plurality of classification trees of the first model to the home's attributes to obtain an estimated valuation of the home; and

applying an aggregation function to the obtained estimated valuations to obtain a first overall valuation of homes in the named geographical area;

at a second time later than the first time:

training a second model that values houses in the named geographical area based on their attributes, using attributes and selling prices for homes in the named geographical area that sold in a second period ending before the second time, the second model being a second forest of classification trees, the second forest comprising a plurality of classification trees, each classification tree of the second forest classifying a plurality of homes and their recent selling prices based on values for the homes of the plurality of a random subset of home attributes;

for each of substantially all of the homes in the named geographical area, applying a plurality of classification trees of the second model to the home's attributes to obtain an estimated valuation of the home; and

applying an aggregation function to the obtained estimated valuations to obtain a second overall valuation of homes in the named geographical; and

generating a display comparing the first and second overall valuations.

7. The non-transitory storage device of claim 6 wherein the display shows the first and second overall valuation.

8. The non-transitory storage device of claim 6 wherein the display shows the magnitude and direction of change from the first overall valuation and the second overall valuation.

9. The non-transitory storage device of claim 6 wherein the display shows the percentage and direction of change from the first overall valuation and the second overall valuation.

10. The non-transitory storage device of claim 6 wherein the display shows the annualized percentage and direction of change from the first overall valuation and the second overall valuation.

11. The non-transitory storage device of claim 6 wherein the generated display superimposes a numerical comparison of the first and second overall valuations over a visual depiction of the named geographical area.

12. The non-transitory storage device of claim 11 wherein the visual depiction is a map.

13. The non-transitory storage device of claim 11 wherein the visual depiction is an aerial photograph.

14. A method in a computer system having a processor for generating a display relating to a named geographic area, the method comprising:

for each of substantially all of the homes in the named geographical area, accessing an estimated current value attributed to the home based on automatically comparing the attributes of the home to attributes of homes recently sold in the named geographic area using each of a plurality of classification trees among a forest of classification trees, each classification tree of the forest classifying a plurality of homes and their recent selling prices based on values for the homes of the plurality of a random subset of home attributes;

with the processor, applying an aggregation function to the accessed estimated current values to obtain an aggregation result; and

causing to be displayed a characterization of the current value of homes in the named geographic area that is based on the aggregation result.

15. A method in a computer system having a processor for displaying a trend in the overall valuation of homes in a named geographical area, the method comprising:

at a first time:

with the processor, training a first model that values houses in the named geographical area based on their attributes, using attributes and selling prices for homes in the named geographical area that sold in a first period ending before the first time, the first model being a first forest of classification trees, the first forest comprising a plurality of classification trees, each classification tree of the first forest classifying a plurality of homes and their recent selling prices based on values for the homes of the plurality of a random subset of home attributes;

for each of substantially all of the homes in the named geographical area, applying a plurality of classification trees of the first model to the home's attributes to obtain an estimated valuation of the home; and

applying an aggregation function to the obtained estimated valuations to obtain a first overall valuation of homes in the named geographical area;

at a second time later than the first time:

training a second model that values houses in the named geographical area based on their attributes, using attributes and selling prices for homes in the named geographical area that sold in a second period ending before the second time, the second model being a second forest of classification trees, the second forest comprising a plurality of classification trees, each classification tree of the second forest classifying a plurality of homes and their recent selling prices based on values for the homes of the plurality of a random subset of home attributes;

for each of substantially all of the homes in the named geographical area, applying a plurality of classification trees of the second model to the home's attributes to obtain an estimated valuation of the home; and

applying an aggregation function to the obtained estimated valuations to obtain a second overall valuation of homes in the named geographical; and

generating a display comparing the first and second overall valuations.