The assignee for this patent application is
Reporters obtained the following quote from the background information supplied by the inventors: "The present disclosure relates to computer processes for detecting and assessing multiple types of risks in financial transactions.
"Many financial transactions are fraught with risks. For example, a mortgage lender may face risks of borrower default and fraud. A fraud detection system may be configured to analyze loan application data to identify applications that are being submitted with fraudulent application data. A separate default risk detection system may be configured to analyze the same application data to address the risk of borrower default.
"However, existing risk detection systems have failed to keep pace with the dynamic nature of financial transactions. Moreover, such systems have failed to take advantage of the increased capabilities of computer systems. Thus, a need exists for improved systems and methods of detecting and assessing various types of risks associated with financial transactions."
In addition to obtaining background information on this patent application, VerticalNews editors also obtained the inventors' summary information for this patent application: "The system, method, and devices disclosed herein each have several aspects, no single one of which is solely responsible for its desirable attributes. Without limiting the scope of the various embodiments as expressed by the claims which follow, the more prominent features of the various embodiments will now be discussed briefly. After considering this discussion, and particularly after reading the section entitled 'Detailed Description of Certain Embodiments,' one will understand how the features of the various embodiments provide advantages that include improved detection and assessment of risks in financial transactions such as mortgage transactions.
"Embodiments disclosed herein provide systems and methods for detecting and assessing various types of risks associated with financial transactions, such as transactions involved in mortgage lending. Embodiments of the risk detection and assessment system combine two or more individual data models that are configured to detect and assess particular types of risks into a single combined model that is better suited for detecting risks in the overall transactions. Various embodiments disclosed herein combine discrete data models, each of which may be utilized on its own to provide a specific risk score. In one embodiment, the data models include at least a model for detecting and assessing mortgage fraud risk, a model for detecting and assessing early mortgage payment default risk, and a multi-component risk model for detecting and assessing risks, with the model based primarily on analysis of data external to a mortgage loan (e.g., analysis of property values in the local market). Other embodiments of the detection and assessment system may include additional models, e.g., a model for detecting the presence of fraudulently reported income data.
"Although the individual models may be capable of predicting individual risks, they may only offer a partial picture of the overall risks. From a risk management standpoint, a user of such predictive models would typically stand to suffer financial losses in mortgage transactions if any of such risks materialize. While it is theoretically possible to apply many or all of these individual models for every loan application, generate scores from all the models and review them, in practice this becomes burdensome on the human reviewers. Indeed, by definition a score is an abstraction of the risks, and the very nature of a risk score is to enable quick detection and assessment of risks without a human review of all the underlying data.
"Therefore, in one embodiment, the combined model takes as input selected scores output by the individual models and potentially other data, processes the selected scores and other data, and generates a single combined score that may reflect an overall risk of a particular transaction. The combined model presents these risks in a comprehensive fashion and is configured to detect potentially hidden risks that may otherwise be difficult to detect by an individual model. Additional performance gains of the combined model over the individual models may include a reduction of false positives, an increase in the dollar amount of identified fraudulent and/or high-risk loans, and an increase in the instances of identified fraudulent and/or high-risk loans.
"In one embodiment, such a combined model may be created based on evaluating the performance of the underlying models (or sets of models) in detecting risks, including fraud and default risks. One or more combined models may be generated by using data including a set of historical transactions in which fraud and/or default outcomes are known. Other combined models may be based on data including, test/training data, current data, real-time data, a mix of historical data, current data, and/or real-time data. Additionally or alternatively, the correlation between the underlying models may be measured, and selected features from the models may be used to create a combined model that is trained on data such as test/training data. The features selected may be based on the type of data analysis modeling structure(s) and technique(s) chosen for the combined model. The performance of the resulting combined model may be evaluated against the performance of the individual models, and adjustments to the combined model may be made to further improve performance.
"The combined models as described herein are especially suitable for mortgage fraud and default detection because many parties are involved in the whole mortgage origination and funding process and mortgage risk exists almost everywhere, from borrowers, to collaterals, to brokers. By combining results from different models having focus in different domains (such as borrower risk, collateral risk, broker risk, identity risk, loan risk, etc.), the combined model(s) provide a more comprehensive and accurate risk assessment of each loan application than any single model alone can provide.
"As disclosed herein, the term 'mortgage' may include residential, commercial, or industrial mortgages. In addition, 'mortgage' may include first, second, home equity, or any other loan associated with a real property. In addition, it is to be recognized that other embodiments may also include risk detection and assessment in other types of loans or financial transactions such as credit card lending and auto loan lending.
BRIEF DESCRIPTION OF THE DRAWINGS
"FIG. 1A is a functional block diagram illustrating a risk detection and assessment system in accordance with an embodiment.
"FIG. 1B is a schematic diagram illustrating an aspect of the combined scoring model that provides an overall risk picture of a mortgage lending transaction.
"FIG. 2 is a flowchart illustrating the operation of the risk detection and assessment system in accordance with an embodiment.
"FIG. 3A is a flowchart illustrating a method of creating a combined model for detecting and assessing risks in financial transactions in accordance with an embodiment.
"FIG. 3B is a flowchart illustrating a method of building a combined model for detecting and assessing risks in financial transactions in accordance with an embodiment.
"FIG. 3C is a flowchart illustrating an embodiment of a method of providing a score indicative of risks using the combined model.
"FIG. 4 is sample report showing a risk score and associated risk indicators generated by the combined model in accordance with an embodiment.
"FIG. 5A is a functional block diagram illustrating the generation and execution of one model in accordance with an embodiment.
"FIG. 5B is a functional block diagram illustrating example models used in the model of FIG. 5A.
"FIG. 5C is a flowchart illustrating another embodiment of model generation for use in the model of FIG. 5A.
"FIG. 6A is a flowchart illustrating a supervised method of generating a model for use in a model that is useable in an embodiment of the risk detection and assessment system.
"FIG. 6B is a flowchart illustrating an unsupervised method of generating a model for use in a model that is useable in an embodiment of the risk detection and assessment system.
"FIG. 7 is a flowchart illustrating an example of using a model based on historical transactions to generate a score indicative of fraud risk for use as part of a combined model in accordance with an embodiment.
"FIG. 8 is a functional block diagram illustrating components of a multi-component risk model that is useable as part of the overall combined model in accordance with an embodiment.
"FIG. 9 is a functional block diagram illustrating the generation and execution of another model that is useable as part of the overall combined model in accordance with an embodiment.
"FIG. 10 is a flowchart illustrating an example of using a model for detecting fraud that is based on applicant income to generate a validity measure for use as part of a combined model in accordance with an embodiment."
For more information, see this patent application: Yan, Rui; Chi, Hoi-Ming; Koo, Seongjoon;
Keywords for this news article include: Mortgage, Real Estate, Legal Issues.
Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2014, NewsRx LLC
Most Popular Stories
- Homeowners More Satisfied With Mortgage Servicers
- House Shelves Immigration Bill, Goes on Vacation
- Ford Tremor: Easy to Park, Hard to Pay For
- What Hamas and Israel Hope to Gain in Gaza
- Notorious RBG Tells All in Couric Interview
- House GOP Leaders Abandon Immigrant Bill
- Why Samsung Shares Plunged in the April-June Quarter
- NASA Plans to Make Oxygen on Mars
- Market Loses All of July's Gains in One Day
- Wisconsin Supreme Court: Voter IDs Must Be Free