Bias detection and estimation under technical portfolio reviews

Patent metadata

Field	Value
Publication number	US-11048741-B2
Application number	US-201916399184-A
Country	US
Kind code	B2
Filing date	Apr 30, 2019
Priority date	Apr 30, 2019
Publication date	Jun 29, 2021
Grant date	Jun 29, 2021

Abstract

A bias detection method, system, and computer program product include creating a context of an applicant based on a profile of the applicant and a context of a reviewer based on a profile of the reviewer, predicting a probability of overlapping data points between the applicant and the reviewer, building enriched embeddings for a deep learning model based on the context of the applicant, the context of the reviewer, the overlapping data points, and text from a review and a final decision by the reviewer, and calculating a bias score via a deep learning model run over the enriched embeddings.

First claim

What is claimed is:

1. A computer-implemented bias detection method for generating a contextual measurement of class and methodological bias in a review processes, the method comprising:
creating a context of an applicant based on a profile of the applicant and a context of a reviewer based on a profile of the reviewer;
predicting a probability of overlapping data points between the applicant and the reviewer;
building enriched embeddings for a deep learning model based on the context of the applicant, the context of the reviewer, the overlapping data points, and text from a review and a final decision by the reviewer; and
calculating a bias score via the deep learning model run over the enriched embeddings,
wherein the bias score includes a combination of:
a class bias;
a methodological bias;
an ecological fallacy;
a reviewer bias;
a reviewer variation; and
an implicit bias.

2. The method of claim 1 , further comprising outputting the bias score to a profile of the reviewer if the bias score is greater than a preset value.

3. The method of claim 1 , further comprising generating a report that highlights instances of bias in the review by the reviewer based on the bias score.

4. The method of claim 2 , further comprising generating a report that highlights instances of bias in the review by the reviewer based on the output bias score.

5. The method of claim 1 , wherein the bias score includes a combination of:
a class bias; and
a position related parameter.

6. The method of claim 1 , embodied in a cloud-computing environment.

7. A computer program product for bias detection, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith for generating a contextual measurement of class and methodological bias in a review processes, the program instructions executable by a computer to cause the computer to perform:
creating a context of an applicant based on a profile of the applicant and a context of a reviewer based on a profile of the reviewer;
predicting a probability of overlapping data points between the applicant and the reviewer;
building enriched embeddings for a deep learning model based on the context of the applicant, the context of the reviewer, the overlapping data points, and text from a review and a final decision by the reviewer; and
calculating a bias score via the deep learning model run over the enriched embeddings,
wherein the bias score includes a combination of:
a class bias;
a methodological bias;
an ecological fallacy;
a reviewer bias;
a reviewer variation; and
an implicit bias.

8. The computer program product of claim 7 , further comprising outputting the bias score to a profile of the reviewer if the bias score is greater than a preset value.

9. The computer program product of claim 7 , further comprising generating a report that highlights instances of bias in the review by the reviewer based on the bias score.

10. The computer program product of claim 8 , further comprising generating a report that highlights instances of bias in the review by the reviewer based on the output bias score.

11. The computer program product of claim 7 , wherein the bias score includes a combination of:
a class bias; and
a position related parameter.

12. A bias detection system for generating a contextual measurement of class and methodological bias in a review processes, the system comprising:
a processor; and
a memory, the memory storing instructions to cause the processor to perform:
creating a context of an applicant based on a profile of the applicant and a context of a reviewer based on a profile of the reviewer;
predicting a probability of overlapping data points between the applicant and the reviewer;
building enriched embeddings for a deep learning model based on the context of the applicant, the context of the reviewer, the overlapping data points, and text from a review and a final decision by the reviewer; and
calculating a bias score via the deep learning model run over the enriched embeddings,

wherein the bias score includes a combination of:
a class bias;
a methodological bias;
an ecological fallacy;
a reviewer bias;
a reviewer variation; and
an implicit bias.

13. The system of claim 12 , further comprising outputting the bias score to a profile of the reviewer if the bias score is greater than a preset value.

14. The system of claim 12 , further comprising generating a report that highlights instances of bias in the review by the reviewer based on the bias score.

15. The system of claim 13 , further comprising generating a report that highlights instances of bias in the review by the reviewer based on the output bias score.

16. The system of claim 12 , wherein the bias score includes a combination of:
a class bias; and
a position related parameter.

17. The system of claim 12 , embodied in a cloud-computing environment.

Assignees

• IBM

Inventors

• Cintas Celia
• Ogallo William
• Walcott Aisha
• Remy Sekou Lionel

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06F40/216

  using statistical methods · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title