Machine Learning and Artificial Intelligence

Artificial intelligence in the form of machine learning (ML) is revolutionizing the science of personnel selection. This will have many benefits to organizations including making the implementation of traditional hiring procedures more efficient, allowing innovations such as novel types of assessments and video interviews, automating the scoring of text information in hiring (such as in applications and resumes, which have been underutilized in the past due to the need for human judgment and the high cost), automating the scoring of interviews, increasing the objectivity of hiring judgments and making them more accurate, and both reducing the potential for discrimination lawsuits and increasing the hiring rates for racial minorities and women. The services we offer include developing ML tools for a wide range of Human Resource purposes, especially personnel selection. We are also commonly asked to independently evaluate vendor products and advise organizations on their use. We conduct bias audits of ML for compliance with state and federal laws as well as for law firms who are seeking expert advice on their clients’ uses of ML.

Example Projects:

  • Developed a computer model for scoring applications and narrative answers for hiring information technology staff.
  • Developed a computer model for scoring applications and narrative answers for hiring administrative and secretarial staff.
  • Conducted a validity and adverse impact analysis of a computer model for scoring applications for hiring professional employees into a large organization.
  • Conducted a plagiarism and AI-generated text analysis of application narratives submitted as part of a hiring process for professional employees to detect candidate cheating.
  • Created computer models for scoring applications for mid career candidates in government professional jobs.
  • Conducted audit to comply with the New York City Automated Employment Decision Tools law.
  • Created algorithms using natural language processing (dictionaries) for scoring range of common interview questions.
  • Used artificial intelligence to create job knowledge and situational judgment tests for contracting, procurement, property management, and other skills.
  • Used artificial intelligence to created bank of interview questions.
  • Created automated interview scoring algorithms for common skills.
  • Analyzed the validity of employment application computer models for predicting assessor scores and the use of the model scores for reducing adverse impact among a large sample of professional employees.
  • Wrote a technical report documenting an external review and validation of a truck driver turnover machine learning (artificial intelligence) prediction model for a large trucking company.
  • Created alternative machine learning models and other analyses to conduct an external validation of a prediction model of truckdriver turnover.
  • Conducted a review of the model building and validity evidence supporting a machine learning prediction model of truckdriver turnover.
  • Analyzed plagiarism and artificial intelligence generated text in employment applications.
  • Conducted an analysis of gender differences in language in 17 dictionaries and 5 samples used for scoring competencies and personality traits for selection.
  • Conducted a validity and adverse impact analysis of a computer model for scoring applications for professional jobs.
  • Guided validation study of an artificial intelligence job analysis tool.
  • Analyzed the use of artificial intelligence generated answer by candidates to applications for hiring into professional jobs for a large organization.
  • Revised integration forms that mathematically combine assessment scores for hiring security engineers, security technicians, and security agents.
  • Conducted an analysis of artificial intelligence generated answers to questions on applications for employment of professional employees in a large organization.
  • Wrote a technical report on the use of natural language processing dictionaries for selection, including 12 datasets and 70,000 candidates.
  • Developed natural language processing (dictionary) computer scoring of competencies for hiring.
  • Revised computer models for scoring writing skill based on essays for hiring.
  • Wrote a technical report documenting the development and validation of computer models for scoring applications to hire professional employees in a large organization.
  • Reviewed software engineering job sample assessment questions for hiring for a financial services company.
  • Conducted NLP computer scoring of employment applications for a large organization.
  • Developed word dictionaries to measure Grti, Resilience, Self-Determination, and Delayed Gratification for hiring and selection into schools.
  • Created New York City Bias Audit reports for distribution to the public for Artificial Intelligence Enabled Tools for a testing company.
  • Advised on hiring HR manager for a small company and reviewed candidates.
  • Reviewed a technical manual for gamified assessments.
  • Criterion validated natural language processing scoring of applications and interviews to measure motivational constructs for hiring, and examining construct validity with other selection procedures.
  • Developed a tool for complying with Artificial Intelligence Bias Audits in New York City.
  • Conduct a New York City Bias Audit of Automated Employment Decision Tools for a large employment test provider.
  • Conducted a study of whether adding competency and personality dictionary scores to other (language based) computer models for hiring professional employees will improve prediction.
  • Conducted an analysis of a computer model for scoring writing skills and an improvement to the model for hiring professional employees.
  • Recorded marketing videos describing the use of artificial intelligence tools to score competencies and personality traits from textual application materials for hiring.
  • Created initial word dictionaries to measure motivational constructs (grit, resilience, self-determination, intrinsic motivation, locus of control, and delayed gratification).
  • Developed word dictionaries for natural language processing scoring of employment applications to measure several motivational constructs, including grit, resilience, self-determination, locus of control, and delayed gratification.
  • Conducted computer scoring of extensive applications and accomplishments descriptions 3 times per year for about 1800 professional candidates since 2014.
  • Wrote a report on the development and validation of word dictionaries to measure the Big-5 personality traits for selection.
  • Conducted a study to determine whether adding competency and personality dictionary scores (using natural language processing) to the current computer models for hiring professional employees can improve prediction of the human hiring official scores.
  • Researched grit, resilience, self-determination, and locus of control to develop a text based measure using artificial intelligence for hiring.
  • Conducted a plagiarism analysis of narratives written in applications for employment, including an analysis of chatbot-written (GPT) narratives.
  • Conducted an analysis of the validity of eight competency dictionaries for hiring in multiple datasets.
  • Validated dictionary-based measures of the Big-5 personality traits against hiring official ratings, including examining construct validity correlations with other personality measures.
  • Conducted an adverse impact analysis of mental ability tests and machine learning (artificial intelligence) models for hiring professional employees in a large organization.
  • Conducted item analyses and reliability analyses of Big-5 dictionary measures.
  • Created word dictionaries for the Big-5 personality traits.
  • Conducted a review and validation of a machine learning (artificial intelligence) model for predicting promotion readiness of processional employees in a large international bank.
  • Wrote a report documenting the development of a dictionary measure of proactivity.
  • Conducted an adverse impact analysis of alternative ways of combining cognitive tests and machine learning (artificial intelligence) assessment scores.
  • Created word dictionary for measuring proactivity from text data in interviews and applications for hiring.
  • Wrote report on developing enthusiasm and empathy dictionaries for scoring interviews.
  • Running computer models to select candidates for professional jobs in a large organization.
  • Analyzed the predictive validity and construct validity of dictionaries to measure enthusiasm and empathy in text scoring of interviews.
  • Conducted validation research on artificial intelligence dictionary measures of enthusiasm and empathy for hiring interviews.
  • Analyzed the accuracy of computer models for scoring applications and essays for hiring in a large organization.
  • Created dictionary to measure empathy in interview responses with artificial intelligence for hiring.
  • Created dictionary to measure enthusiasm interview responses with artificial intelligence for hiring.
  • Prepared update on new developments in the assessment world and use of artificial intelligence for Board Meeting.
  • Assisted in creating an artificial intelligence interview scoring product by developing design, functionality, administration, and content.
  • Write several hundred interview items for an artificial intelligence interview scoring product.
  • Analyzing the relationship between computer scoring of an application and resume with human scores.
  • Wrote an interview item bank of 350 questions to be used for an artificial intelligence interview product.
  • Analyzed TF-IDF and other scoring methods for artificial intelligence competency measures for hiring.
  • Conducted analyses of various artificial intelligence scores for measuring competencies.
  • Developed competency dictionaries to inform hiring decisions as a product for a start up artificial intelligence company.
  • Created dictionaries for scoring the competencies reflected in written application materials.
  • Reviewed of the development method, validity, and adverse impact of artificial intelligence computer models for prescreening job candidates at a large organization.
  • Running computer models to score candidate applications and resumes.
  • Provided a review of computer models for hiring professional employees based on personnel selection practices, validation evidence, adverse impact, and legal exposure, as well as machine learning.
  • Analyzed computerized text analysis scores of application information to create personality composites for selection decisions at schools.
  • Analyzing the validity of computer models for predicting assessor scores in a large-scale hiring process.
  • Created composites for reporting computerized text scores to report to clients for a personality-based hiring product.
  • Conducted analyses to determine text-based personality composites to use in an online product.
  • Conducted a study and wrote report replicating the prediction of a computer model for hiring medical professionals.
  • Conducted a study and wrote report on a diversity and adverse impact analysis of a computer model for hiring medical professionals.
  • Conducted an analysis of the adverse impact of computer models for selecting students into graduate medical training, including the predictive value of alternative selection procedures to reduce impact.
  • Conducted a review of an artificial intelligence application for screening resumes for a personnel section from an Industrial Psychology research perspective for a data science company.
  • Conducted an analysis of the accuracy of computer models for scoring applications for employment in a large government agency.
  • Reviewing the literature and creating dictionaries for a range of constructs for an artificial intelligence employment selection algorithm.
  • Reviewed a computer model for scoring resumes for hiring for a large company.
  • Review the validation study for an artificial intelligence (machine learning) model for reviewing applications and resumes for hiring managers into a large company.
  • Writing articles (blog posts) on artificial intelligence for an AI assessment vender.
  • Analyzed the accuracy of computer models based on correlations with human assessors for scoring applications that include extensive narratives and essays used for hiring professional employees.
  • Provided an independent analysis of the accuracy of a machine learning (artificial intelligence) computer model for selecting medical school candidates.
  • Analyzed the accuracy of computer models for scoring applications and essays.
  • Evaluating the products of a start-up company in the area of artificial intelligence tools for hiring.
  • Conducted analyses of the accuracy of computer models to predict human assessor scores of applications and essays.
  • Conducted an analysis of the utility and adverse impact of computer scoring (artificial intelligence) models.
  • Wrote a report cross-validating and developing a final computer model for scoring the writing skill in essays for hiring professional employees.
  • Conduct analyses of the validity of text analyses of application information, including incremental validity beyond aptitude tests, for predicting selection decisions of officers in the military.
  • Conducted text mining of candidate applications in the military and correlated with selection board scores.
  • Analyzed correlations between computer scores and assessor scores of hiring procedures for professional employees in a large organization.
  • Wrote a technical report on the development and validation of a text-mining computer model for scoring essays for writing skills to hire professional employees.
  • Created a text mining computer model to score writing skills based on essays written by job candidates for professional jobs.
  • Conducted computer scoring of application data for a large number of candidates.
  • Conducted training of text analysis computer models to enhance job relatedness and content validity.
  • Conducted test mining of interview questions and and analyzed correlations with mental ability tests.
  • Reviewed a report on the use of machine learning for reclassification of personnel in the Air Force.
  • Developed computer assisted text analysis models of interview answers.
  • Reviewed validation studies of a computer scoring (machine learning) model for prescreening resumes at a large organization.
  • Conducted analysis of computer assisted text analysis of sentiment by demographics.
  • Finalized literature review on use of computer assisted text analysis for measuring employment-related constructs.
  • Conducted sentiment analyses on employee survey responses using two sets of software.
  • Conducted text mining of applicant information for hiring.
  • Ran computer scoring model on applicant data and analyses to improve the computer model (including text mining).
  • Conducted an literature review and wrote a report on the use of computer assisted text analysis for hiring, training, and appraisal.
  • Conducted text mining of essay responses to create a computer model for hiring.
  • Revised the computer model for scoring applicant text and other application information for hiring professional employees in a large organization.
  • Conducted literature review of the use of text mining.
  • Reviewed applicability of text mining and computer learning to measure hiring-related constructs in the military.
  • Analyzing the accuracy of a computer model for predicting assessor scores in a hiring context.
  • Reviewed a machine learning report on scoring application information for hiring.
  • Reviewed a machine learning (data mining) report for scoring applications.
  • Conducted a test equating study and set a passing score on an automated writing assessment for hiring financial professional employees.
  • Reviewed a proposal to proceed with a computerized resume scoring process for hiring programmers in a large company.
  • Text mining (computer scoring) candidate essay application information for hiring into a professional occupation.
  • Conducted a statistical study of the stability of computer scoring of candidate essays over time.
  • Reviewed proposal to develop a machine learning algorithm for scoring assessments for hiring into a large organization.
  • Conducted an analysis of the relationship between computer scores and assessor scores on accomplishment records and application materials.
  • Analyzed the correlations between computer and assessor scores of accomplishment records to determine equivalency in a large scale hiring process.
Please contact us for more information on how Campion Consulting Services can enhance your organizational capabilities.