Skip to content
Technology & Innovation

Phai Labs, the R&D arm of PredictiveHire, announces a world-first algorithm to deliver unmatched accuracy and explainability in language based job assessments.

MELBOURNE, Australia

PredictiveHire, the creator of the world’s Smartest Interviewer, today announced its world-first innovation – InterviewBERT – which uses Google’s model for Natural Language Processing (NLP) to understand the contextual meaning of words in written job interviews.

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

The result is a best-in-class 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 question-answer tasks with keyword matching, and is capable of discovering personality traits and communication skills all from a candidate’s written text.
PredictiveHire is in a unique position to innovate in this area because of its proprietary data set accumulated through Phai conducting a Smart Interview every 30 seconds, combined with the deep expertise of the Phai Labs team that has meant Phai can assess the suitability for a role in milliseconds.
PredictiveHire CEO Hyman said the innovation meant that the company could claim to be the market leader when it came to accurately determining the suitability of candidates using text-based interviews.

“The smartest companies know that the fairest and most accurate way to assess someone’s suitability for a role is through a structured Interview. Text increases accuracy and speed of assessing candidates while removing biases that come through voice or video interviews,” Hyman said.

Dr Buddhi Jayatilleke, who heads up the R&D team at Phai Labs and is the company’s Chief Data Scientist, said the team were excited at the finding that InterviewBERT had such a profound impact on trait accuracy.

“Written language encodes personality signals predictive of “fit”,” Dr Jayatilleke said. “The ability to understand people through language has limitless applications and we are excited to keep inventing more ways to use language data for our customers. ”

Dr Jayatilleke said decades of research had confirmed that language has long been seen as a source of truth for personality.

“What our R&D team has proven is just how powerful language data is when you combine it with enormous data volumes and scientific rigour,” he said.
“This capability can be used for assessment and for offering personalised career coaching – a game changer for job seekers, universities, and employers.”

Phai Labs will present their findings from their 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 like the 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 party proprietary text data and advanced Natural Language Processing, we turn simple text conversations into unprecedented talent intelligence enabling organisations to interrupt hiring bias at scale, get to the right talent fast and give every candidate an experience they love.

SOURCE PredictiveHire

Source: PredictiveHire