System and method for facilitating real estate transactions by analyzing user-provided data

1. A computer-implemented method of identifying a home to facilitate a real estate transaction, the method comprising:

(a) generating a plurality of different neural network objects, wherein each object in the plurality of neural network objects includes (i) a respective neural network model, (ii) a respective landmark address, and (iii) a respective landmark image;

(b) training, for each object in the plurality of neural network objects, the respective neural network model in the each object to emit a respective confidence score, by the respective neural network model analyzing the respective landmark image in the each object to identify respective key features;

(c) receiving an example address and an example image;

(d) selecting, based on the example address, a set of trained neural network objects from the plurality of neural network objects, wherein each object in the set of trained neural network objects includes (i) a trained neural network model, (ii) a landmark address, and (iii) a landmark image;

(e) generating a set of confidence scores, by applying the example image to the trained neural network model in each object of the set of trained neural network objects,

wherein each confidence score in the set of confidence scores corresponds to a respective object in the set of trained neural network objects, and

wherein applying the example image to the trained neural network model in each object of the set of trained neural network objects includes analyzing the example image to identify example key features;

(f) generating, based on the set of confidence scores, a result set, wherein the result set includes at least one landmark address and at least one landmark image, both corresponding to a trained neural network object in the set of trained neural network objects;

(g) transmitting, to a user device, the result set; and

(h) causing, in the user device, one or both of (i) the at least one result landmark address and (ii) the at least one result landmark image to be displayed.

2. The method of claim 1 , wherein generating a set of confidence scores, by applying the example image to the trained neural network model in each object of the set of trained neural network objects, includes comparing the example key features corresponding to the example image to key features of the landmark image corresponding to the trained neural network object.

3. The method of claim 2 , further comprising counting the number of key features corresponding to the example image to key features of the landmark image corresponding to the trained neural network object.

4. The method of claim 1 , further comprising:

ranking, according to the set of confidence scores, the result set.

5. The method of claim 1 , wherein generating, based on the set of confidence scores, a result set, wherein the result set comprises at least one landmark address and at least one landmark image, both corresponding to a trained neural network object in the set of trained neural network objects includes retrieving, from a remote device, additional information corresponding to the at least one landmark address, and decorating the result set with the additional information.

6. The method of claim 5 , wherein the additional information includes one or more of (i) real estate listing information, (ii) a mortgage offer, and (iii) a home insurance offer.

7. The method of claim 1 , wherein (d) and (e) are iteratively repeated until at least one confidence score is within a predetermined threshold.

8. The method of claim 1 , further comprising:

receiving a user indication corresponding to the at least one landmark image;

repeating, based on the user indication corresponding to the at least one landmark image, (d), (e), (f), (g), and (h).

9. The method of claim 1 , wherein key features correspond to one or both of (i) manmade features, and (ii) natural features.

10. The method of claim 1 , wherein the at least one result landmark address and the at least one result landmark image correspond to one or both of (i) a similar landmark image, and (ii) a nearby landmark address.

11. A computing system comprising:

one or more processors; and

one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to:

(a) generate a plurality of different neural network objects, wherein each object in the set plurality of neural network objects includes (i) a respective neural network model, (ii) a respective landmark address, and (iii) a respective landmark image;

(b) train, for each object in the plurality of neural network objects, the neural network model in the each object to emit a confidence score, by the neural network model analyzing the landmark image in the each object to identify key features;

(c) receive an example address and an example image;

(d) select, based on the example address, a set of trained neural network objects from the plurality of neural network objects, wherein each object in the set of trained neural network objects includes (i) a trained neural network model, (ii) a landmark address, and (iii) a landmark image;

(e) generate a set of confidence scores, by applying the example image to the trained neural network model in each object of the set of trained neural network objects;

wherein each confidence score in the set of confidence scores corresponds to a respective object in the set of trained neural network objects, and

wherein applying the example image to the trained neural network model in each object of the set of trained neural network objects includes analyzing the example image to identify example key features;

(f) generate, based on the set of confidence scores, a result set, wherein the result set includes at least one landmark address and at least one landmark image, both corresponding to a trained neural network object in the set of trained neural network objects;

(g) transmit, to a user device, the result set; and

(h) cause the user device to display one or both of (i) the at least one result landmark address and (ii) the at least one result landmark image.

12. The computing system of claim 11 , wherein the instructions further cause the computing system to:

rank, according to the set of confidence scores, the result set.

13. The computing system of claim 11 , wherein the instructions further cause the computing system to:

retrieve, from a remote device, additional information corresponding to the at least one landmark address; and

decorate the result set with the additional information.

14. The computing system of claim 13 , wherein the additional information includes one or more of (i) real estate listing information, (ii) a mortgage offer, and (iii) a home insurance offer.

15. The computing system of claim 11 , wherein (d) and (e) are iteratively repeated until at least one confidence score is within a predetermined threshold.

16. The computing system of claim 11 , wherein the instructions further cause the computing system to:

receive a user indication corresponding to the at least one landmark image;

repeat, based on the user indication corresponding to the at least one landmark image, (d), (e), (f), (g), and (h).

17. The computing system of claim 11 , wherein key features correspond to one or both of (i) manmade features, and (ii) natural features.

18. The computing system of claim 11 , wherein the at least one result landmark address and the at least one result landmark image correspond to one or both of (i) a similar landmark image, and (ii) a nearby landmark address.

19. A non-transitory computer readable medium containing program instructions that when executed, cause a computer to:

(a) generate a plurality of different neural network objects, wherein each object in the plurality of neural network objects includes (i) a respective neural network model, (ii) a respective landmark address, and (iii) a respective landmark image;

(b) train, for each object in the plurality of neural network objects, the respective neural network model in the each object to emit a respective confidence score, by the neural network model analyzing the respective landmark image in the each object to identify respective key features;

(c) receive an example address and an example image;

(d) select, based on the example address, a set of trained neural network objects from the plurality of neural network objects, wherein each object in the set of trained neural network objects includes (i) a trained neural network model, (ii) a landmark address, and (iii) a landmark image;

(e) generate a set of confidence scores, by applying the example image to the trained neural network model in each object of the set of trained neural network objects,

wherein each confidence score in the set of confidence scores corresponds to a respective object in the set of trained neural network objects, and

wherein applying the example image to the trained neural network model in each object of the set of trained neural network objects includes analyzing the example image to identify example key features;

(f) generate, based on the set of confidence scores, a result set, wherein the result set includes at least one landmark address and at least one landmark image, both corresponding to a trained neural network object in the set of trained neural network objects;

(g) transmit, to a user device, the result set; and

(h) cause the user device to display one or both of (i) the at least one result landmark address and (ii) the at least one result landmark image.

20. The non-transitory computer readable medium of claim 19 , wherein the instructions further cause the computer to:

rank, according to the set of confidence scores, the result set.