Version 1.0

Latent Dirichlet Allocation (LDA)  based topic model for scoring

Single RESTful API, section scores of skills, work experience, education, certification, awards / interest, resume drop, steady job, total work experience,

location score (score based on distance from job location), resume raw scoring –  Entire JD vs Entire resume textInputs – Job description extracted text, Resume extracted Text, Section text extracted from resume for skills, work experience, education, certification and awards, Location – Zipcode / Postal code, Output: Overall score

Version 2.0

• LDA Scoring Model – Normalization updates for final score

• Implemented Individual API split for all scoring component mentioned in the output of v1.0

• Enhancements for improving response time

• Moved Data processing to Parser

Version 2.1:

• Fixes and Handler for scoring a Bad job (Job description does not have more than 40 words)

• Fixes for LDA score  > 100

• Fixes for removing duplicate parsed data for each section of resume

Version 3.0:

• Implemented RoBERTa based Deep Learning Transformer model to give similarity score for resume components –  Skill score, Work experience score, Education score, Awards / Interests score, Certifications score, raw score

Version 3.1:

• Implemented LDA Score for Skill score, Certification score, education score

• Implemented RoBerta based transformer model similarity score for Work experience and Interests / Awards score

Version 4.0:

• Updated to RoBERTa model for all components (skill, work experience, education, awards/certifications, interests)

• Added weights to final scores of skill and work experience section

• Exploring further optimizations to improve performance speed

Version 5.0:

• Geescore’s scoring service combines advanced parsing and intelligent scoring techniques, that are bias-free, without subjective inferences, to transform recruitment workflows. Using state-of-the-art prompt instruction models, the service parses resumes with exceptional accuracy, extracting and creating structured data sections such as skills, work experience, certifications and education.
• The model includes derived parameters such as location, commuting distance and others. The scoring engine employs techniques such as zero-shot classification and similarity scoring to match and evaluate resumes against specific job criteria, ensuring precise alignment. This approach delivers unmatched insights, empowering businesses to identify the most suitable candidates in seconds.
• We have gone through multiple advances in the scoring service including validation, eliminating bias, improved speed and more.
• The Geescore jobseeker scoring service determines suitability of a jobseeker (resume) to a specific job (job posting) maintaining the integrity of resumes and job postings as reliable data sources. We use all means possible, including AI Fraud detection of hyper-optimized resumes, as well as procedures to identify fungible jobs using embeddings to remediate poor job postings, and prevent AI abuses.

We are pleased to share the science and business logic of the Geescore™Jobseeker Scoring solution. It is a dynamic hybrid approach to scoring based on constant improvement; lowering bias, increasing objectivity, and score validation. Currently we use a hybrid:

• Deep Transformer model for work experience, skills, education, working domain and
• Classic scoring algorithms, with 3 levels of matching science, as well as real-world recruiting parameters, for derived attributes such as job matches, steady job, location, etc.