Abstract: A system and method for analyzing a subject appraisal detects discrepancies and determines likely causes. This is done by accessing several data structures which correspond to appraisals that each contain data regarding property characteristics of a particular property. Data for different appraisals is then compared according to one or more rules. Depending on the result of the comparison and in light of the rules, a message, flag, or warning may be generated. In this manner, possible instances of fraud or misrepresentation may be detected.

Abstract: The present invention relates to a mapping and comparing choroplethic housing statistics. In one example, this comprises accessing property data corresponding to a geospatial area. Analytics are used to generate usable property data statistics from the accessed property data. A thematic map image based on the usable property data statistics is then generated according to comparison categories, so that the thematic map image may be displayed.

Abstract: Automated valuation model with customizable neighborhood determination. A map image is displayed corresponding to a geographical area, and then user input accommodates definition of a particularly defined geographic area to provide custom identification of a neighborhood to be subject to automated valuation. Once the defined geographic area is established, the automated valuation model is applied to property data corresponding to properties within the defined geographic area. A subject property and corresponding properties within the defined geographic area are then displayed on a map image, preferably with articulation of the defined geographic area as the neighborhood of interest. The neighborhood may be defined by, among other criteria, inclusion within a user-defined shape, as well as exclusion of a user-defined shape from a displayed geographic area.

Abstract: Modeling appropriate comparable properties for the assessment of appraisals entails accessing a property dataset, wherein subsets of properties represented in the property data are determined to be members of respective condominium projects. Condominium project identification information is scrubbed, standardized and updated using various techniques. An automated valuation model is applied to the property data, preferably implementing the condominium project variable as a location fixed effect variable. Appraisal reports where the subject property is a condominium are then analyzed using the results of the automated valuation model, including but not limited to ranking and displaying the appraiser-chosen comparables among the model-chosen comparables.

Abstract: A system and method for appraisal adjustments scoring rates the quality of adjustments made by appraisers in their appraisals of real property. This is done by accessing a model adjustment database that is based on an automated valuation model and a peer adjustment database that is based on an aggregate of appraiser peers in the same geographic location as the subject property. A comparison is conducted for adjustments made by the appraiser to both model adjustments and peer adjustments to determine discrepancies. When a discrepancy is larger than a threshold, a message or warning may be generated. A sales pool composition database is also accessed to determine a valuation impact of the flagged adjustments given the particular set of comparable sales selected by the appraiser. After data evaluation, a rating score is calculated for the property appraisal based on the number and severity of messages and the valuation impact.

Abstract: A system and method may aggregate into a data structure property information from multiple databases, e.g., from all records included in those databases, and upon selection of any subject property or a characteristic thereof curates the often imperfect and discrepant property information to create suggested values. Similarly, the system and method may perform an on-the-fly evaluation of any characteristic of a selected record, when the property information for that characteristic includes an unlikely value, by triggering from the data structure a dynamic extraction of property information corresponding to a subject property of the selected record, where the dynamic extraction further generates and compares a suggested value to the unlikely value.

Abstract: A comparable property selection system and method employs dynamic gating in the selection of comparable properties. When the most restrictive comparable selection algorithm fails to identify enough comparable sales to use as inputs to the downstream analytics processes, the system does not simply expand the pool or solely expand the corresponding geographical area. Instead, the system automatically loosens and tightens property search filters iteratively to expand and shrink the size of a local geographic and economic market to locate comparables that have property characteristics that most closely reflect the real estate market considerations a buyer, or an appraiser acting as a buyer, would evaluate in a heterogeneous market.

Abstract: Performing automated appraisals with automatic detection and remediation of situations involving faulty characteristics is disclosed. Property information characteristics are extracted from properties listed on electronic appraisals. For a subject property, faulty characteristics include the absence of characteristics, or errors in characteristics. Such faulty characteristics are those that would cause an automated appraisal of the given property to be invalid or unsuitable. In response to the detection of faulty characteristics, interfaces may solicit input addressing the faulty characteristic and upon remediation indicate a clean and complete characteristic set. Thereafter, automated appraisal of the subject property based on the clean characteristic set is initiated to provide an automated valuation of the subject property.

Abstract: A device including a memory with an automated collateral fraud and risk detection application installed thereon, wherein the application determines whether a final appraised value of an appraisal was correctly reconciled from comparable properties listed on the appraisal by extracting reconciliation information from the appraisal, the reconciliation information including adjusted sale prices for each comparable property listed on the appraisal and the final appraised value; applying a rule set to the reconciliation information to generate sub-scores; applying a heuristic to the sub-scores to generate a reconciliation score; and outputting a scorecard for the appraisal based on the reconciliation score.

Abstract: An appraisal error detection method includes accessing a database of appraisal-data-field entries of property appraisals. Because sales transactions are cited repetitively as comparables on multiple appraisals, it is possible to inspect appraisal-data-field entries for consistency. An error detection operation is performed for each of the corresponding appraisal-data-field entries by detecting any discrepancies, both between appraisers, and between different appraisals by the same appraisers, where corresponding appraisal-data-field entries are for a same property characteristic of a same property. Appraisal-data-field entries determined by the error detection operation to be erroneous are flagged, and a discrepancy score may be assigned to flagged erroneous entries that indicates an amount of risk posed by the entry. Appraisals in the database may be assigned a score based upon the sum of their entries' discrepancy scores.

Abstract: A system comprises a device including a memory with an automated collateral fraud and risk detection application installed thereon, wherein the application detects receives a plurality of sequential underwriting submissions, compares corresponding data fields of each sequential underwriting submission to identify whether the corresponding data fields include inconsistent information, and determines if the inconsistent information is indicative of the underwriting manipulation.

Abstract: A system comprises a device including a memory with a risk detection application installed thereon, wherein the risk detection application detects strategic defaulters by generating a rule set in response to receiving a search query, the rule set including a plurality of rules that respectively identify strategic default characteristics determined to correspond to a potential strategic default status, each of the plurality of rules having a corresponding weight; accessing a record in a database of loan information; applying the plurality of rules to determine whether the strategic default characteristics are respectively represented in the record; calculating a strategic defaulter score for the record using the corresponding weights for those of the plurality of rules that are determined to be represented in the record; and outputting the strategic defaulter score for the record.

Abstract: A system comprises a device including a memory with an automated collateral fraud and risk detection application installed thereon, wherein the application evaluates risk in an acquisition in support of end user decisions by accessing at least one database to retrieve documentation corresponding to the acquisition and secondary information corresponding to the documentation, the documentation and secondary information each including data fields; compares the documentation data fields with corresponding secondary information data fields to identify acquisition defects; applies risk heuristics on the acquisition defects to generate a probability estimation for each acquisition defect; and outputs a risk evaluation for the acquisition including a confidence metric based on an aggregation of the probability estimations.

Abstract: Automated valuation model with customizable neighborhood determination. A map image is displayed corresponding to a geographical area, and then user input accommodates definition of a particularly defined geographic area to provide custom identification of a neighborhood to be subject to automated valuation. Once the defined geographic area is established, the automated valuation model is applied to property data corresponding to properties within the defined geographic area. A subject property and corresponding properties within the defined geographic area are then displayed on a map image, preferably with articulation of the defined geographic area as the neighborhood of interest. The neighborhood may be defined by, among other criteria, inclusion within a user-defined shape, as well as exclusion of a user-defined shape from a displayed geographic area.

Abstract: The present invention relates to photograph initiated property assessment. In one example, an electronic device performs a photograph initiated property assessment by accessing a photographic assessment itinerary that includes a plurality of target portions for the subject property and a set of image capture requirements for each of the plurality of target portions. Further, when performing the initiated property assessment the electronic device prompts a plurality of image capture requests according to the photographic assessment itinerary while displaying a menu that permits the addition of information to the set of image captures.

Abstract: A method for location triggered home evaluation for an electronic device that determines a location of the electronic device and identifies a subject property associated with the location. Further, a set of appraisal information for the subject property that includes a listing of comparable properties determined to be appropriate comparable properties for the subject property is requested.

Abstract: A method for automatic detection of inconsistencies in an appraisal by extracting data from the appraisal to create component data arranged into a predetermined set of categories and selecting a control identifier to trigger a generation of comparison data. Further, through a comparison between the comparison data and the component data, inconsistencies within the appraisal are identified.

Abstract: The present invention relates to a mapping and comparing choroplethic housing statistics. In one example, this comprises accessing property data corresponding to a geospatial area. Analytics are used to generate usable property data statistics from the accessed property data. A thematic map image based on the usable property data statistics is then generated according to comparison categories, so that the thematic map image may be displayed.

Abstract: Automated valuation model with customizable neighborhood determination. A map image is displayed corresponding to a geographical area, and then user input accommodates definition of a particularly defined geographic area to provide custom identification of a neighborhood to be subject to automated valuation. Once the defined geographic area is established, the automated valuation model is applied to property data corresponding to properties within the defined geographic area. A subject property and corresponding properties within the defined geographic area are then displayed on a map image, preferably with articulation of the defined geographic area as the neighborhood of interest. The neighborhood may be defined by, among other criteria, inclusion within a user-defined shape, as well as exclusion of a user-defined shape from a displayed geographic area.

Abstract: An automated valuation model and corresponding analysis tool that graphically displays value history information in association with a subject property is disclosed. In one example, the tool generates a graph plotting the valuation history of a subject property over an adjustable time range in relation to a general price index for a pertinent geographical area. When looking at an appraisal for a property, the graph also supports selective plotting of appraiser-selected comparable properties' valuation histories against that of the subject property. The valuation history for comparable properties can be scaled on a pro-rata basis according to the percentage of the adjustments made within the appraisal. In addition, the graph selectively incorporates model-generated comparables and their valuation histories.