How do PredictiveHire determine who gets marked as Yes, No or Maybe?

There are over 40 different factors that go into determining whether someone gets categorised as a Yes, No or a Maybe. 

Our machine learning measures each and every one these different factors, or data points, which fall under 5 main areas.

  1. Readability: AKA how easy the text is to understand. This includes complexity of the vocabulary and syntax. We incorporate a number of internationally recognised formulas to measure this, such as the Fleisch-Kincaid scale.
  2. Semantic alignment: this looks at how an applicant’s answers aligns with the answers of previous hires.
  3. Sentiment: How positive is the message? How subjective is it?
  4. Text structure and quality: this includes a total sentence count, word count, ratio of verbs/nouns/pronouns etc. We also look at the quality of spelling, grammar, and punctuation.
  5. Personality: we map the text answers supplied against the HEXACO framework to analyse the applicant’s personality.

At the end of the questionnaire these different factors are analysed, compared with applicants who have been hired into the same role, and then allocated to the Yes, No or Maybe categories. Generally speaking, in terms of the possibility of being hired,

  • Yes: represents the top 40%
  • Maybe: represents the middle 20%
  • No: represents the bottom 40%

Like with everything in life, this isn't a guarantee they'll be successful, but our prediction based on the factors we've mentioned above. 

We're not here to replace recruiters, but to help you use your time better. Think of us as you would about using Boolean search to locate candidates. It helps you distill down a large pool into a much more manageable one, but you still need to make the decision on who are the right people to move forward with.

It's almost inevitable that you will see someone who doesn't fit, or isn't right for you role, particularly in the beginning. As we learn what good looks like for your business you can help us by categorising your applicants regularly. 


See Also:

What do the different status' mean?

Why does my shortlist look different?

What if the Yes candidate isn't right?

What if the No candidate is right?