Systems, methods, and computer products for model-based query assignment
A system is disclosed that includes a database and a processor in communication with the database. The processor is configured to maintain a data structure comprising historical value data and historical condition data and receive a query requesting a streamlined process. The processor is further configured to, based on the query, make a first assessment whether a submitted value ratio is within a predetermined range of a modeled value ratio; make a second assessment whether the modeled value ratio exceeds a predetermined maximum; and, based on the first assessment and the second assessment, assign a first flag to the query. The processor is further configured to based on the query, instantiate a condition model by obtaining the historical condition data; assign a second flag to the query; and based on the first flag and the second flag, determine whether to assign the query to the streamlined process.
1. A system comprising:
a database;
a processor in communication with the database; and
a memory device, in communication with the processor, storing instructions that, when executed by the processor, perform operations comprising:
maintaining at the database a data structure comprising historical value data and historical condition data;
receiving a query requesting a streamlined process, wherein the query comprises submitted value data;
based on the query, instantiating a value model by:
obtaining the historical value data from the database and determining, based on the historical value data, a modeled value ratio,
determining, based on the submitted value data, a submitted value ratio, wherein the modeled value ratio and the submitted value ratio represent a common characteristic, and wherein the modeled value ratio and the submitted value ratio are determined based on the historical value data and the submitted value data, respectively,
making a first assessment whether the submitted value ratio is within a predetermined range of the modeled value ratio,
making a second assessment whether the modeled value ratio exceeds a predetermined maximum, and
based on the first assessment and the second assessment,
assigning a first flag to the query;
further based on the query, instantiating a condition model by:
obtaining the historical condition data from the database, and
based on the historical condition data, assigning a second flag to the query, wherein the condition model is configured to determine a quantitative metric by processing one or more qualitative indicators of the historical condition data, and wherein the second flag is assigned based on comparison of the quantitative metric; and
based on the first flag and the second flag, determining whether to assign the query to the streamlined process.
2. The system of claim 1 , wherein:
if the submitted value ratio is within the predetermined range of the modeled value ratio and the modeled value ratio does not exceed the predetermined maximum, the first flag comprises an instruction to assign the query to the streamlined process; and
if the submitted value ratio is not within the predetermined range of the modeled value ratio or the modeled value ratio exceeds the predetermined maximum, the first flag comprises an instruction not to assign the query to the streamlined process.
3. The system of claim 1 , wherein determining whether to assign the query to the streamlined process based on the first flag and the second flag comprises:
if either of the first flag or the second flag comprises an instruction not to assign the query to the streamlined process, determining not to assign the query to the streamlined process; and
if each the first flag and the second flag comprises an instruction to assign the query to the streamlined process, determining to assign the query to the streamlined process.
4. The system of claim 1 , wherein the data structure further comprises historical fraud data, the operations further comprising:
based on the query, instantiating a fraud model by:
obtaining the historical fraud data from the database, and
based on the historical fraud data, assigning a third flag to the query,
wherein determining whether to assign the query to the streamlined process based on the first flag and the second flag comprises determining whether to assign the query to the streamlined process based on the first flag, the second flag, and the third flag.
5. The system of claim 1 , wherein determining whether to assign the query to the streamlined process based on the first flag, the second flag, and the third flag comprises:
if any of the first flag, the second flag, and the third flag comprises an instruction not to assign the query to the streamlined process, determining not to assign the query to the streamlined process; and
if each the first flag, the second flag, and the third flag comprises an instruction to assign the query to the streamlined process, determining to assign the query to the streamlined process.
6. The system of claim 1 , wherein maintaining the data structure comprises aggregating the historical value data and the historical condition data from at least one other database.
7. A method comprising:
maintaining at a database a data structure comprising historical value data and historical condition data;
receiving a query requesting a streamlined process, wherein the query comprises submitted value data;
based on the query, instantiating a value model by:
obtaining the historical value data from the database and determining, based on the historical value data, a modeled value ratio,
determining, based on the submitted value data, a submitted value ratio, wherein the modeled value ratio and the submitted value ratio represent a common characteristic, and wherein the modeled value ratio and the submitted value ratio are determined based on the historical value data and the submitted value data, respectively,
making a first assessment whether the submitted value ratio is within a predetermined range of the modeled value ratio,
making a second assessment whether the modeled value ratio exceeds a predetermined maximum, and
based on the first assessment and the second assessment, assigning a first flag to the query;
further based on the query, instantiating a condition model by:
obtaining the historical condition data from the database, and
based on the historical condition data, assigning a second flag to the query, wherein the condition model is configured to determine a quantitative metric by processing one or more qualitative indicators of the historical condition data, and wherein the second flag is assigned based on comparison of the quantitative metric; and
based on the first flag and the second flag, determining whether to assign the query to the streamlined process.
8. The method of claim 7 , wherein:
if the submitted value ratio is within the predetermined range of the modeled value ratio and the modeled value ratio does not exceed the predetermined maximum, the first flag comprises an instruction to assign the query to the streamlined process; and
if the submitted value ratio is not within the predetermined range of the modeled value ratio or the modeled value ratio exceeds the predetermined maximum, the first flag comprises an instruction not to assign the query to the streamlined process.
9. The method of claim 7 , wherein determining whether to assign the query to the streamlined process based on the first flag and the second flag comprises:
if either of the first flag or the second flag comprises an instruction not to assign the query to the streamlined process, determining not to assign the query to the streamlined process; and
if each the first flag and the second flag comprises an instruction to assign the query to the streamlined process, determining to assign the query to the streamlined process.
10. The method of claim 7 , wherein the data structure further comprises historical fraud data, the operations further comprising:
based on the query, instantiating a fraud model by:
obtaining the historical fraud data from the database, and
based on the historical fraud data, assigning a third flag to the query,
wherein determining whether to assign the query to the streamlined process based on the first flag and the second flag comprises determining whether to assign the query to the streamlined process based on the first flag, the second flag, and the third flag.
11. The method of claim 7 , wherein determining whether to assign the query to the streamlined process based on the first flag, the second flag, and the third flag comprises:
if any of the first flag, the second flag, and the third flag comprises an instruction not to assign the query to the streamlined process, determining not to assign the query to the streamlined process; and
if each the first flag, the second flag, and the third flag comprises an instruction to assign the query to the streamlined process, determining to assign the query to the streamlined process.
12. The method of claim 7 , wherein maintaining the data structure comprises aggregating the historical value data and the historical condition data from at least one other database.
13. A tangible computer readable media that store software instructions that, when executed by one or more processors, are configured for and capable of performing and executing a method comprising:
maintaining at a database a data structure comprising historical value data and historical condition data;
receiving a query requesting a streamlined process, wherein the query comprises submitted value data;
based on the query, instantiating a value model by:
obtaining the historical value data from the database and determining, based on the historical value data, a modeled value ratio,
determining, based on the submitted value data, a submitted value ratio, wherein the modeled value ratio and the submitted value ratio represent a common characteristic, and wherein the modeled value ratio and the submitted value ratio are determined based on the historical value data and the submitted value data, respectively,
making a first assessment whether the submitted value ratio is within a predetermined range of the modeled value ratio,
making a second assessment whether the modeled value ratio exceeds a predetermined maximum, and
based on the first assessment and the second assessment, assigning a first flag to the query;
further based on the query, instantiating a condition model by:
obtaining the historical condition data from the database, and
based on the historical condition data, assigning a second flag to the query, wherein the condition model is configured to determine a quantitative metric by processing one or more qualitative indicators of the historical condition data, and wherein the second flag is assigned based on comparison of the quantitative metric; and
based on the first flag and the second flag, determining whether to assign the query to the streamlined process.
14. The tangible computer readable media of claim 13 , wherein the method further comprises:
if the submitted value ratio is within the predetermined range of the modeled value ratio and the modeled value ratio does not exceed the predetermined maximum, the first flag comprises an instruction to assign the query to the streamlined process; and
if the submitted value ratio is not within the predetermined range of the modeled value ratio or the modeled value ratio exceeds the predetermined maximum, the first flag comprises an instruction not to assign the query to the streamlined process.
15. The tangible computer readable media of claim 13 , wherein determining whether to assign the query to the streamlined process based on the first flag and the second flag comprises:
if either of the first flag or the second flag comprises an instruction not to assign the query to the streamlined process, determining not to assign the query to the streamlined process; and
if each the first flag and the second flag comprises an instruction to assign the query to the streamlined process, determining to assign the query to the streamlined process.
16. The tangible computer readable media of claim 13 , wherein the data structure further comprises historical fraud data, the method further comprising:
based on the query, instantiating a fraud model by:
obtaining the historical fraud data from the database, and
based on the historical fraud data, assigning a third flag to the query,
wherein determining whether to assign the query to the streamlined process based on the first flag and the second flag comprises determining whether to assign the query to the streamlined process based on the first flag, the second flag, and the third flag.
17. The tangible computer readable media of claim 13 , wherein determining whether to assign the query to the streamlined process based on the first flag, the second flag, and the third flag comprises:
if any of the first flag, the second flag, and the third flag comprises an instruction not to assign the query to the streamlined process, determining not to assign the query to the streamlined process; and
if each the first flag, the second flag, and the third flag comprises an instruction to assign the query to the streamlined process, determining to assign the query to the streamlined process.
18. The tangible computer readable media of claim 13 , wherein maintaining the data structure comprises aggregating the historical value data and the historical condition data from at least one other database.