Thursday, 22 June 2017

How to Rank Resumes ?



In an email to Prof Rahul Deshmukh ( IIT – Mumbai ) , I had suggested following approach :




Feb 18 , 2013



Dear Team


Google calls it PageRank – to decide the importance of a web page – then use this number to decide the rank ( position ) of that page within the search results


Let us follow Google ( very safe ! )


And call our “ Ranking Mechanism “ of any given resume , a “ Pa-Rank


Then arrange all arriving resumes ( in the mailbox of a Recruiter or on our web site ), in the descending order of their Pa-Rank


Highest ranked at the top


So , the Recruiter need to open / read only the top 5 - 7  !  No  more  !


In much the same manner that 95% of the searchers never go beyond the first 3 pages of any search-result despite millions of pages


Just imagine how much time it will save the recruiters to zero-in on the best candidates from amongst hundreds applying for any given job


This has the potential to revolutionize the On-line recruitment industry !


How can we determine a candidate’s Pa-Rank ?


Just like PageRank , which takes into account,


#   No of Incoming links to a given page

#   Importance of each incoming link ( based on its own incoming links )


No doubt , Google’s actual algorithm must be very complex – and continues to evolve


Thru our mobile app , “ Resume Blaster “ ( and someday , thru app “ My Jobs “ as well ), we pick-up the “ Contact List “ ( of mobile nos ) of say, Ajay ( a user registered on our site )


These are his “ Primary Incoming Links “ – say , 40


Out of these 40 , say , 10 have also registered on our site AND , are also using our mobile app “ Resume Blaster


In turn , these 10 have , between them , 600 contacts ( “ Secondary Incoming Links “ )


So , for Ajay , total Incoming links =  40+600 =  640


Now , if Ajay thinks he has figured out how our software computes Pa-Rank then he will somehow find out the mobile number of Mukesh Ambani , and add into his “ Contacts “ – assuming that at one stroke ,he can add ONE MILLION incoming links to himself !


But , we know that such high-flying executives are unlikely to have registered on our site – much less , to be using our app , “ Resume Blaster “ !


Hence we treat this as a “ Dead Incoming Link


On top of that , we can further refine our Pa-Rank based on,


#   The frequency with which Ajay keeps calling each of those 10 persons ( who have registered on our site AND are also using our app “ Resume Blaster “ )


#   The duration of each call ( or even text message ? )


We can multiply / sum-up / find average ,  etc of such “ exchanges of messages – both ways “ and arrive at some “ FACTOR


Then multiply the “  Total No of Live Incoming Links “ with this “ FACTOR “ , to compute PaRank


Looks crude , no doubt !


But Google has proved that it works !


What PageRank is for all the web pages in the World , someday , PaRank will be to all the resumes ( which too , like any web page , are documents ) , in India


We must do it !


On internet , “ Ideas are dime-a-dozen “


But elegant executions are rare !




8 years earlier ( on 21 Dec 2005 ) , I had sent the following proposal to the Shri Ashish Kashyap ( the then Country Manager - Google India ) :






It was only this week that Google launched “ Google Job Search “ ( for USA jobs )


I am sure someone in Google will read this blog – then implement it to change the rules of Online Recruitment Industry !





23  June  2017







No comments:

Post a Comment