METHODS AND SYSTEMS FOR RISK MINING AND FOR GENERATING ENTITY RISK PROFILES
A computer implemented method for mining risks includes providing a set of risk-indicating patterns on a computing device; querying a corpus using the computing device to identify a set of potential risks by using a risk-identification-algorithm based, at least in part, on the set of risk-indicating patterns associated with the corpus; comparing the set of potential risks with the risk-indicating patterns to obtain a set of prerequisite risks; generating a signal representative of the set of prerequisite risks; storing the signal representative of the set of prerequisite risks in an electronic memory; and aggregating potential risks linked to an entity to an entity risk profile (ERP). A computing device or system for mining risks includes an electronic memory; and a risk-identification-algorithm based, at least in part, on the set of risk-indicating patterns associated with a corpus stored in the electronic memory.
1 . A computer implemented method comprising:
a. automatically analyzing by a computer a set of linguistic characteristics of a set of information associated with an entity;
b. based upon the step of automatically analyzing, automatically generating by the computer an entity-specific risk profile (“ERP”) associated with the entity, the entity-specific risk profile comprising a first risk component and a second risk component; and
c. storing the entity-specific risk profile in a memory accessible by the computer.
2 . The method of claim 1 wherein the first risk component and the second risk component are from a group comprising a financial risk component, a legal risk component, an operational risk component, and a markets risk component.
3 . The method of claim 1 wherein the entity-specific risk profile further comprises a third risk component and a fourth risk component.
4 . The method of claim 3 wherein the third risk component and the fourth risk component are from a group comprising a financial risk component, a legal risk component, an operational risk component, and a markets risk component.
5 . The method of claim 1 , wherein the set of information is derived from a corpus of electronic documents.
6 . The method of claim 5 , wherein the corpus is one or more of a group consisting of news, financial information, legal information, regulatory information, blogs, and event streams.
7 . The method of claim 6 , wherein automatically analyzing a set of linguistic characteristics comprises identifying a set of entity-specific risks based at least in part on a set of risk-indicating patterns associated with the corpus.
8 . The method of claim 1 , wherein automatically analyzing a set of linguistic characteristics comprises identifying a set of entity-specific risks by using a risk-identification-algorithm.
9 . The method of claim 8 , wherein the risk-identification-algorithm is based at least in part on one or more of a group consisting of a set of terms statistically associated with risk; a temporal factor; a set of customized criteria, including one or more of industry criterion, geographic criterion, monetary criterion, and political criterion.
10 . The method of claim 1 further comprising automatically transmitting an entity-specific alert upon detecting that the entity-specific risk profile meets or exceeds a predetermined risk value.
11 . The method of claim 1 further comprising automatically comparing a first entity-specific risk profile associated with a first entity with a second entity-specific risk profile associated with a second entity.
12 . The method of claim 11 further comprising using the results of comparing a first entity-specific risk profile associated with a first entity with a second entity-specific risk profile associated with a second entity to develop a risk-balanced portfolio of companies/securities comprising a fund or portfolio.
13 . The method of claim 1 further comprising providing an electronic link with the entity-specific risk profile to link a representation of the first risk component with the set of information from which the first risk component was derived.
14 . The method of claim 1 , wherein the entity is one of a group consisting of a company, a person, a politically exposed person (PEP), an industry, a sector, and a member of a corporate team.
15 . The method of claim 1 , wherein automatically analyzing by a computer a set of linguistic characteristics of a set of information associated with an entity includes applying a risk-based taxonomy.
16 . The method of claim 15 , wherein the risk-based taxonomy is learned from the set of information.
17 . The method of claim 1 , wherein the first risk component and the second risk component are from a group comprising: general risks; idiosyncratic risks, self trend; and peer trend.
18 . The method of claim 1 further comprising predicting a risk trend based on an historic time series.
19 . The method of claim 18 wherein predicting a risk trend based on an historic time series further comprises applying a smoothing operation to mitigate outliers.
20 . The method of claim 1 further comprising generating a set of ERPs associated respectively with a set of entities.
21 . A computer-based system comprising:
a processor adapted to execute code;
a memory for storing executable code;
an input adapted to receive a set of information derived from a set of media information sources;
a first set of code when executed by the processor being adapted to automatically analyze a set of linguistic characteristics of the set of information, and to identify risks associated with an entity;
a second set of code when executed by the processor being adapted to automatically generate an entity-specific risk profile (“ERP”) associated with the entity based on the identified risks and to store the ERP in the memory, the entity-specific risk profile comprising a first risk component and a second risk component; and
an output adapted to transmit a signal associated with the generated ERP.
22 . The system of claim 21 wherein the first risk component and the second risk component are from a group comprising a financial risk component, a legal risk component, an operational risk component, and a markets risk component.
23 . The system of claim 21 wherein the entity-specific risk profile further comprises a third risk component and a fourth risk component.
24 . The system of claim 23 wherein the third risk component and the fourth risk component are from a group comprising a financial risk component, a legal risk component, an operational risk component, and a markets risk component.
25 . The system of claim 21 , wherein the set of information is derived from a corpus of electronic documents.
26 . The system of claim 25 , wherein the corpus is one or more of a group consisting of news, financial information, legal information, regulatory information, blogs, and event streams.
27 . The system of claim 26 , wherein the second set of code adapted to automatically analyze a set of linguistic characteristics further comprises code which when executed by the processor is adapted to identify a set of entity-specific risks based at least in part on a set of risk-indicating patterns associated with the corpus.
28 . The system of claim 21 , wherein the second set of code adapted to automatically analyze a set of linguistic characteristics further comprises code which when executed by the processor is adapted to identify a set of entity-specific risks by using a risk-identification-algorithm.
29 . The system of claim 28 , wherein the risk-identification-algorithm is based at least in part on one or more of a group consisting of a set of terms statistically associated with risk; a temporal factor; a set of customized criteria, including one or more of industry criterion, geographic criterion, monetary criterion, and political criterion.
30 . The system of claim 21 further comprising a third set of code when executed by the processor being adapted to automatically transmit an entity-specific alert upon detecting that the entity-specific risk profile meets or exceeds a predetermined risk value.
31 . The system of claim 21 further comprising a fourth set of code when executed by the processor being adapted to automatically compare a first entity-specific risk profile associated with a first entity with a second entity-specific risk profile associated with a second entity.
32 . The system of claim 31 further comprising a fifth set of code when executed by the processor being adapted to use the results from execution of the fourth set of code to generate an output representative of a recommended risk-balanced portfolio of companies/securities comprising a fund or portfolio.
33 . The system of claim 21 , wherein the ERP comprises an electronic link linking the first risk component with the set of information from which the first risk component was derived.
34 . The system of claim 21 , wherein the entity is one of a group consisting of a company, a person, a politically exposed person (PEP), an industry, a sector, and a member of a corporate team.
35 . The system of claim 21 , wherein the first set of code adapted to automatically analyze the set of linguistic characteristics of the set of information includes a set of code adapted to apply a risk-based taxonomy to identify risks.
36 . The system of claim 35 , wherein the risk-based taxonomy is learned from the set of information.
37 . The system of claim 21 , wherein the first risk component and the second risk component are from a group comprising: general risks; idiosyncratic risks, self trend; and peer trend.
38 . The system of claim 21 further comprising a set of trend code when executed by the processor is adapted to predict a risk trend based on an historic time series.
39 . The system of claim 38 wherein the set of trend code further comprises a set of smoothing code adapted to perform a smoothing operation on data related to the historic time series to mitigate outliers.
40 . A computer implemented automated method comprising:
a. aggregating a set of risk related information;
b. generating a categorized set of risk related information by associating the set of risk related information with at least one risk type from a set of risk types, the set of risk types comprising an operational risk type, a legal risk type, a markets risk type, and a financial risk type; and
c. electronically storing the categorized set of risk related information.
41 . The method of claim 40 , wherein generating a categorized set of risk related information includes applying a risk-based taxonomy.
42 . The method of claim 41 , wherein the risk-based taxonomy is learned at least in part from a corpus of electronic documents.
43 . The method of claim 40 , wherein the set of risk related information is derived at least in part from a corpus of electronic documents.
44 . The method of claim 43 , wherein the corpus is one or more of a group consisting of news, financial information, legal information, regulatory information, blogs, and event streams.
45 . The method of claim 40 , wherein aggregating the set of risk related information includes automatically analyzing a set of linguistic characteristics to identify a set of entity-specific risks based at least in part on a set of risk-indicating patterns associated with the corpus.
46 . The method of claim 40 , wherein aggregating the set of risk related information includes automatically analyzing a set of linguistic characteristics to identify a set of entity-specific risks by using a risk-identification-algorithm.
47 . The method of claim 40 , wherein generating a categorized set of risk related information is based at least in part on one or more of a group consisting of a set of terms statistically associated with risk; a temporal factor; a set of customized criteria, including one or more of industry criterion, geographic criterion, monetary criterion, and political criterion.
48 . The method of claim 40 , wherein the set of risk related information is associated with one or more entities.