Estimating the cost of residential remodeling projects

1. A method in a computing system for analyzing a home remodeling project, comprising:

for each particular project among one or more completed first projects:

receiving, by the computer system, a photograph of a room depicting a completed state of the particular project;

receiving, by the computer system, an identification of one or more of a plurality of characteristics of the particular project shown in the photograph;

evaluating one or more rules to impute one or more additional characteristics of the project not shown in the photograph by:

identifying a type of the home remodeling project corresponding to one or more of a remodel of a particular room, a landscaping project, or a swimming pool installation;

identifying a pre-determined set of project characteristics corresponding to the identified type of the home remodeling project; and

imputing a characteristic value for one or more distinguished project characteristics of the pre-determined set of project characteristics that does not have a value specified through analysis of the photograph by applying the one or more rules matching the one or more distinguished project characteristics such that characteristics of a portion of the room not depicted in the photograph are selected; and

obtaining, by the computer system via a graphical user interface, an estimated cost for the particular project;

training, by the computer system, a project cost model that predicts project cost wherein the training is performed using, for each of the first projects, its identified characteristics, imputed one or more additional characteristics, and obtained cost;

receiving, by the computer system, an identification of one or more of the plurality of characteristics for a second project;

applying, by the computer system, the trained project cost model to the identified one or more of the plurality of characteristics for the second project to obtain an estimated cost for performing the second project; and

causing, by the computer system, the obtained estimated cost for performing the second project to be displayed via the graphical user interface.

2. The method of claim 1 , further comprising receiving a date,

wherein applying the trained project cost model comprises applying the trained project cost model to the received date as well as to the identified characteristics of the second project and a received geographic location to obtain an estimated cost for performing the second project in the received geographic location on the received date.

3. The method of claim 1 , wherein, for at least one of the first projects, the photograph depicting the completed state of the particular project is an image printed in a magazine or a catalog, or a photograph taken of a sample house.

4. The method of claim 1 , wherein the imputation is further based on a statistical imputation model.

5. The method of claim 1 , wherein the imputed one or more additional characteristics indicate 1) whether an item exists in the room, 2) the model or style of an item that exists in the room, 3) how many instances of an item exist in the room, or 4) the model or style of the room.

6. The method of claim 1 ,

wherein, when the type is a kitchen remodel, one of the imputed one or more additional characteristics indicates that a microwave, a dishwasher, a refrigerator, or a stove exists in a kitchen, or

wherein, when the type is a bathroom remodel, one of the imputed one or more additional characteristics indicates that a mirror or a sink exists in a bathroom.

7. The method of claim 1 , wherein one of the imputed one or more additional characteristics indicates that:

no more than one chandelier light is in the room,

no more than two flush lights are in the room,

no more than two sconce lights are in the room,

or no more than one pendant light is in the room and the room a bathroom.

8. The method of claim 1 ,

wherein the obtained estimated cost for each particular project is in relation to a particular geographic location;

wherein the training the project cost model is further performed using the particular geographic location for each particular project; and

wherein the applying the trained project cost model comprises providing a received geographic location for the second project to the trained project cost model.

9. The method of claim 1 further comprising:

receiving a second photograph of a second room depicting a completed state of the second project; and

evaluating the one or more rules to impute one or more second characteristics of the second project not shown in the second photograph based on a portion of the second room not depicted in the second photograph; and

wherein the applying the trained project cost model comprises providing the one or more second characteristics, of the second project, to the trained project cost model.

10. A computer-readable hardware memory having contents configured to cause a computing system to perform a method of analyzing a home remodeling project, the method comprising:

for each particular project of one or more completed first projects:

receiving, by the computer system, a photograph of a room depicting a completed state of the particular project;

receiving, by the computer system, an identification of one or more of a plurality of characteristics, shown in the photograph, for the particular project;

evaluating one or more rules to impute one or more additional characteristics of the project not shown in the photograph by:

identifying a type of the home remodeling project:

identifying a pre-determined set of project characteristics corresponding to the identified type of the home remodeling project; and

imputing a characteristic value for one or more distinguished project characteristics of the pre-determined set of project characteristics that does not have a value specified through analysis of the photograph by applying the one or more rules matching the one or more distinguished project characteristics such that characteristics of a portion of the room not depicted in the photograph are selected; and

obtaining, by the computer system via a graphical user interface, an estimated cost for the particular project;

training, by the computer system, a project cost model that predicts project cost wherein the training is performed using, for each of the first projects, its identified characteristics, imputed one or more additional characteristics, and obtained cost;

receiving, by the computer system, an identification of one or more of the plurality of characteristics for a second project;

applying, by the computer system, the trained project cost model to the identified one or more of the plurality of characteristics for the second project to obtain an estimated cost for performing the second project; and

causing, by the computer system, the obtained estimated cost for performing the second project to be displayed via the graphical user interface.

11. The computer-readable hardware memory of claim 10 , the method further comprising receiving a date,

wherein applying the trained project cost model comprises applying the trained project cost model to the received date as well as to the identified characteristics of the second project and a received geographic location to obtain an estimated cost for performing the second project in the received geographic location on the received date.

12. The computer-readable hardware memory of claim 10 , wherein, for at least one of the first projects, the photograph depicting the completed state of the particular project is an image printed in a magazine or a catalog, or a photograph taken of a sample house.

13. The computer-readable hardware memory of claim 10 , wherein the imputation is further based on a statistical imputation model.

14. The computer-readable hardware memory of claim 10 , wherein the imputed one or more additional characteristics indicate 1) whether an item exists in the room, 2) the model or style of an item that exists in the room, 3) how many instances of an item exist in the room, or 4) the model or style of the room.

15. The computer-readable hardware memory of claim 10 ,

wherein, when the type is a kitchen remodel, one of the imputed one or more additional characteristics indicates that a microwave, a dishwasher, a refrigerator, or a stove exists in a kitchen, or

wherein, when the type is a bathroom remodel, one of the imputed one or more additional characteristics indicates that a mirror or a sink exists in a bathroom.

16. The computer-readable hardware memory of claim 10 , wherein one of the imputed one or more additional characteristics indicates that:

no more than one chandelier light is in the room,

no more than two flush lights are in the room,

no more than two sconce lights are in the room, or

no more than one pendant light is in the room and the room is a bathroom.

17. The computer-readable hardware memory of claim 10 , wherein the method further comprises:

receiving a second photograph of a second room depicting a completed state of the second project; and

evaluating the one or more rules to impute one or more second characteristics of the second project not shown in the second photograph by applying a rule matching one or more of the plurality of characteristics shown in the photograph to select characteristics of a portion of the second room not depicted in the second photograph; and

wherein the applying the trained project cost model comprises providing the one or more second characteristics, of the second project, to the trained project cost model.

18. The computer-readable hardware memory of claim 10 ,

wherein the obtained estimated cost for each particular project is in relation to a particular geographic location;

wherein the training the project cost model is further performed using the particular geographic location for each particular project; and

wherein the applying the trained project cost model comprises providing a received geographic location for the second project to the trained project cost model.

19. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:

for each particular project of one or more completed first projects:

receive a photograph of a room depicting a completed state of the particular project;

receive an identification of one or more of a plurality of characteristics, shown in the photograph, for the particular project;

evaluate one or more rules to impute one or more additional characteristics of the project not shown in the photograph based on:

identifying a type of the home remodeling project:

identifying a pre-determined set of project characteristics corresponding to the identified type of the home remodeling project; and

imputing a characteristic value for one or more distinguished project characteristics of the pre-determined set of project characteristics that does not have a value specified through analysis of the photograph by applying the one or more rules matching the one or more distinguished project characteristics; and

obtain, via a graphical user interface, an estimated cost for the particular project;

train a project cost model that predicts project cost wherein the training is performed using, for each of the first projects, its identified characteristics, imputed one or more additional characteristics, and obtained cost;

receive an identification of one or more of the plurality of characteristics for a second project;

apply the trained project cost model to the identified one or more of the plurality of characteristics for the second project to obtain an estimated cost for performing the second project; and

cause the obtained estimated cost for performing the second project to be displayed via the graphical user interface.

20. The apparatus of claim 19 , the at least one memory and the computer program code configured to, with the processor, cause the apparatus to further receive a date,

wherein applying the trained project cost model comprises applying the trained project cost model to the received date as well as to the identified characteristics of the second project and a received geographic location to obtain an estimated cost for performing the second project in the received geographic location on the received date.