System and method for subjective property parameter determination
In variants, the method for subjective property scoring can include determining an objective score for a subjective characteristic of a property using a model trained using subjective property rankings.
1. A method comprising:
determining a property;
determining a set of measurements of the property; and
determining an objective score for a subjective characteristic of the property based on the set of measurements using a model trained on a set of training properties ranked based on the subjective characteristic using qualitative labels.
2. The method of claim 1 , wherein the training properties are manually ranked based on the subjective characteristic using qualitative labels; wherein the model is trained by:
determining an objective score for each training property based on the respective ranking; and
training the model to predict the objective score, based on a set of measurements for the respective training property.
3. The method of claim 2 , wherein the sets of measurements for each training property have substantially the same measurement quality.
4. The method of claim 2 , wherein the sets of measurements for each training property and the property are sampled from the same poses relative to the respective property.
5. The method of claim 1 , wherein the objective score for each training property is determined based on a rating for the training property, wherein the rating is determined from the respective ranking using a rating model.
6. The method of claim 1 , wherein the objective score is a categorical variable value.
7. The method of claim 6 , wherein the model is trained by:
determining a categorical variable value for each training property based on the respective rank of the training property within the set; and
training the model to predict the categorical variable value based on a set of measurements for the training property.
8. The method of claim 1 , wherein the method further comprises determining a property valuation based on the objective score.
9. The method of claim 1 , wherein the method further comprises providing the objective score and at least one image of the property to a user.
10. The method of claim 1 , wherein the set of measurements comprises an oblique image of the property.
11. The method of claim 1 , wherein the set of measurements comprises an interior image of a building of the property.
12. The method of claim 1 , wherein the subjective characteristic comprises curb appeal.
13. A system, comprising:
a storage device; and
a set of processors coupled to the storage device, the storage device storing software instructions for controlling the set of processors that, when executed, cause the set of processors to:
determine an image of a property of interest; and
determine an appeal score for the property based on the image using a scoring model trained on a set of training properties ranked by subjective appeal using qualitative labels.
14. The system of claim 13 , wherein the scoring model is trained to predict an appeal score indicative of the ranking for each of the set of training properties.
15. The system of claim 13 , wherein training the model comprises:
determining a rating for each training property based on the respective ranking; and
training the model to predict an appeal score indicative of the rating based on an image of the respective training property.
16. The system of claim 13 , wherein the ranks for the set of training properties are manually determined by displaying images of two training properties to a user and receiving a user preference between the two training properties.
17. The system of claim 13 , wherein the ranks for the set of training properties are determined based on images of the training properties, wherein all images have substantially a same image quality and each image is taken from substantially a same pose relative to the respective property.
18. The system of claim 13 , wherein the system is further configured to return at least one of the appeal scores or an image of the property of interest.
19. The system of claim 13 , wherein the system is further configured to determine a property modification for the property of interest based on the appeal score.
20. The system of claim 13 , wherein the system is further configured to determine a property valuation for the property of interest based on the appeal score.