# US 2021/0279598 A1 · Methods and systems for processing data having varied temporal characteristics to generate predictions related to management arrangements using random forest classifiers

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0279598 A1
- Document ID: US20210279598A1
- Status: Published application
- Kind: A1
- Application number: 16/810,724
- Filed: 2020-03-05
- Published: 2021-09-09
- Earliest claimed: 2020-03-05
- Assignees: UBS Business Solutions AG
- Applicants: UBS Business Solutions AG
- Inventors: Hayden Thomas Luse; David Andrew DiCiurcio; Ronald Jansen
- Web page: https://patentgrep.com/patent/US20210279598A1

## CPC

- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Methods and systems are described for processing data having varied temporal characteristics to generate predictions related to management arrangements using random forest classifiers. For example, the system may receive first data related to a first management arrangement of a first entity and a second management arrangement of a second entity. The system may receive an output from the random forest classifier related to a predicted second management transformation. The system may then generate for display, in a user interface, a prediction based on the predicted second management transformation.

## Claims

### Claim 1

A method of processing data having varied temporal characteristics to generate predictions related to management arrangements using random forest classifiers, the method comprising:
receiving, using control circuitry, first data related to a first management arrangement of a first entity, wherein the first data comprises a first temporal characteristic and a first management transformation of the first entity;
generating, using the control circuitry, a first feature vector for the first data, wherein a first element of the first feature vector corresponds to the first temporal characteristic;
training, using the control circuitry, a random forest classifier based on the first feature vector to classify the first data as corresponding to the first management transformation;
receiving, using the control circuitry, second data related to a second management arrangement of a second entity, wherein the second data comprises a second temporal characteristic and an unknown management transformation of the second entity;
generating, using the control circuitry, a second feature vector for the second data, wherein a second element of the second feature vector corresponds to the second temporal characteristic;
inputting, using the control circuitry, the second feature vector into the random forest classifier;
receiving, using the control circuitry, an output from the random forest classifier related to a predicted second management transformation; and
generating for display, in a user interface, a prediction based on the predicted second management transformation.

### Claim 2 (depends on 1)

The method of claim 1, further comprising transforming the output from an exponential distribution to a probability based on a Bayes classifier, wherein the prediction includes the probability.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
determining a first datum of the first data that is indicative of the first management transformation;
determining a second datum of the second data that corresponds to the first datum; and
generating for display a representation of the second datum in the prediction.

### Claim 4 (depends on 3)

The method of claim 3, further comprising:
determining a first value for the first datum that is indicative of the first management transformation;
determining a second value of the second datum that corresponds to the first value; and
generating for display a representation of the second value in the prediction.

### Claim 5 (depends on 1)

The method of claim 1, wherein the random forest classifier is a time series classifier, and wherein the predicted second management transformation has a third temporal characteristic.

### Claim 6 (depends on 1)

The method of claim 1, wherein the first management transformation comprises a launching of a first activism campaign against the first management arrangement, and wherein the prediction based on the predicted second management transformation comprises a probability of a launching of a second activism campaign against the second management arrangement.

### Claim 7 (depends on 1)

The method of claim 1, wherein training the random forest classifier based on the first feature vector to classify the first data as corresponding to the first management transformation comprises backtesting the random forest classifier against historical data related to historical management arrangements and historical management transformations.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
receiving a user input initiating a review of publicly available data related to management arrangements for a plurality of entities; and
in response to the review, query a data source for the second data, wherein the second data is received in response to querying the data source.

### Claim 9 (depends on 1)

The method of claim 1, further comprising:
generating for display respective predictions for a plurality of entities based on publicly available data related to management arrangements for the plurality of entities; and
ranking the second entity among the plurality of entities based on a comparison of the prediction and the respective predictions.

### Claim 10 (depends on 1)

The method of claim 1, further comprising:
receiving third data related to a third management arrangement of a third entity, wherein the third data comprises a third temporal characteristic and a third management transformation of the third entity;
determining a similarity of the third data and the second data; and
generating for display, in the user interface, a comparison of the second entity and the third entity based on the similarity, wherein the comparison includes an outcome of the third management transformation.

### Claim 11

A non-transitory computer-readable medium for processing data having varied temporal characteristics to generate predictions related to management arrangements using random forest classifiers, comprising instructions that, when executed by one or more processors, cause operations comprising:
receiving first data related to a first management arrangement of a first entity, wherein the first data comprises a first temporal characteristic and a first management transformation of the first entity;
generating a first feature vector for the first data, wherein a first element of the first feature vector corresponds to the first temporal characteristic;
training a random forest classifier based on the first feature vector to classify the first data as corresponding to the first management transformation;
receiving second data related to a second management arrangement of a second entity, wherein the second data comprises a second temporal characteristic and an unknown management transformation of the second entity;
generating a second feature vector for the second data, wherein a second element of the second feature vector corresponds to the second temporal characteristic;
inputting the second feature vector into the random forest classifier;
receiving an output from the random forest classifier related to a predicted second management transformation; and
generating for display, in a user interface, a prediction based on the predicted second management transformation.

### Claim 12 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the instructions further cause operations comprising transforming the output from an exponential distribution to a probability based on a Bayes classifier, wherein the prediction includes the probability.

### Claim 13 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the instructions further cause operations comprising:
determining a first datum of the first data that is indicative of the first management transformation;
determining a second datum of the second data that corresponds to the first datum; and
generating for display a representation of the second datum in the prediction.

### Claim 14 (depends on 13)

The non-transitory computer-readable medium of claim 13, wherein the instructions further cause operations comprising:
determining a first value for the first datum that is indicative of the first management transformation;
determining a second value of the second datum that corresponds to the first value; and
generating for display a representation of the second value in the prediction.

### Claim 15 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the random forest classifier is a time series classifier, and wherein the predicted second management transformation has a third temporal characteristic.

### Claim 16 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the first management transformation comprises a launching of a first activism campaign against the first management arrangement, and wherein the prediction based on the predicted second management transformation comprises a probability of a launching of a second activism campaign against the second management arrangement.

### Claim 17 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein training the random forest classifier based on the first feature vector to classify the first data as corresponding to the first management transformation comprises backtesting the random forest classifier against historical data related to historical management arrangements and historical management transformations.

### Claim 18 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the instructions further cause operations comprising:
receiving a user input initiating a review of publicly available data related to management arrangements for a plurality of entities; and
in response to the review, query a data source for the second data, wherein the second data is received in response to querying the data source.

### Claim 19 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the instructions further cause operations comprising:
generating for display respective predictions for a plurality of entities based on publicly available data related to management arrangements for the plurality of entities; and
ranking the second entity among the plurality of entities based on a comparison of the prediction and the respective predictions.

### Claim 20 (depends on 11)

The non-transitory computer-readable medium of claim 11, wherein the instructions further cause operations comprising:
receiving third data related to a third management arrangement of a third entity, wherein the third data comprises a third temporal characteristic and a third management transformation of the third entity;
determining a similarity of the third data and the second data; and
generating for display, in the user interface, a comparison of the second entity and the third entity based on the similarity, wherein the comparison includes an outcome of the third management transformation.
