Phai Labs, the R&D arm of PredictiveHire, announces a globally unique algorithm delivering unparalleled accuracy and explainability in language-based job assessments.


Melbourne, Australia, February 9, 2022 /PRNewswire/ — PredictiveHire, makers of the world’s smartest interviewer, today announced its first global innovation – InterviewBERT – which uses Google’s natural language processing (NLP) model to understand contextual meaning. words in written job interviews.

The Phai Labs team adapted BERT (Bidirectional Encoder Representations of Transformers), the world’s best natural language pre-training algorithm, to create InterviewBERT by applying PredictiveHire’s proprietary dataset of over 330 million of words collected from 1.2 million candidates. for jobs in 47 countries.

The result is a top-notch algorithm for understanding the contextual meaning of words in interview responses that cements Phai, the chatbot powered by InterviewBERT, as the smartest interviewer on the market.

Phai is not a simple chat-bot that automates Q&A tasks with keyword matching, and is able to uncover personality traits and communication skills from a candidate’s written text.
PredictiveHire is in a unique position to innovate in this area due to its proprietary dataset accumulated by Phai conducting a smart interview every 30 seconds, combined with the deep expertise of the Phai Labs team that has enabled Phai to assess role suitability in milliseconds.
PredictiveHire CEO Hyman said the innovation meant the company could claim to be the market leader when it came to accurately determining candidate suitability using text-based interviews.

“The smartest companies know that the fairest and most accurate way to assess a person’s suitability for a position is through a structured interview. Text increases the accuracy and speed of job evaluation. candidates while removing the biases that arise from voice or video interviews,” Hyman said.

Doctor Buddhi Jayatillekewho leads Phai Labs’ R&D team and is the company’s chief data scientist, said the team was excited to find that InterviewBERT had such a profound impact on trait accuracy.

“Written language encodes personality cues predictive of ‘fit,'” Dr. Jayatilleke said. linguistic data for our customers.”

Dr Jayatilleke said decades of research have confirmed that language has long been considered a source of truth for personality.

“What our R&D team has proven is how powerful linguistic data is when you combine it with huge volumes of data and scientific rigor,” he said.
“This capability can be used for assessment and to offer personalized career coaching – a game changer for job seekers, universities and employers.”

Phai Labs will present the results of its latest research paper on “Identifying and Mitigating Gender Bias in Structured Interview Responses” at a SIOP (The Society for Industrial and Organizational Psychology) symposium in April.

PredictiveHire’s customers include global brands such as Qantas Group and Afterpay.

About PredictiveHire

PredictiveHire’s mission is to help companies unlock and engage talent at scale. Using the world’s first Smart Interviewer, powered by the world’s largest source of 1st proprietary text data and advanced natural language processing, we transform simple text-based conversations into unprecedented talent intelligence enabling organizations to interrupt hiring bias at scale, quickly access the right talent and provide each candidate with an experience they love.


View original content: – and-explicability-in-language-based-job-assessments-301478215.html

SOURCE Predictive Hire


Comments are closed.