Saturday, 24 June 2017

Of Interest to Recruiters / Job Portals



Yesterday , I attended a seminar on CHAT BOTS , conducted by Beerud Sheth ( www.GupShup.io )



Leaving aside the technical part ( which was beyond me ) , I realized that the time has come for some of my ideas , which I jotted down , way back in Jan 2007 , in the margins of the book :



ARTIFICIAL INTELLIGENCE APPLICATION PROGRAMMING ( M. Tim Jones )


I believe , someday soon , either some start up in the Online Recruitment space or one of the major Job Portal ( Naukri / MonsterIndia / TimesJobs / LinkedIn ), will implement these ideas



I have no doubt , Beerud ( beerud@gupshup.io ) would be able to create appropriate BOTs for each of these ideas ( and , even make these BOTs talk to each other ) , for a few thousand dollars !



I wonder why people are worrying about ROBOTS replacing humans in distant future



To me , the issue is : How many human jobs, will BOTS take away in near future ?



For Recruiters / Headhunters , that answer lies on  Pages  142 / 300 /388  !



Here are those notes scribbled in the margins of the book :




Page  3

·         We are planning that “ weights “ of each keyword gets automatically adjusted / updated dynamically , with arrival of each new resume in our database . We only provide the “ seeds “ – the starting weights . Inputs are “ Keywords “ / Outputs are “ Raw Scores


Page  4

·         This would be of interest to us . Job Advts posted ( on any job site ) are nothing but expressions of a Company’s “ staffing requirements “ . 

If we have 5,000 job advts for a given Company ( over past 3 years ), we should be able to find a time-series / trend and should be able to predict its “ future “ requirements . Simplest is extrapolation of past trends !


Page  47

·         We have talked of a concept like Rubik’s Cube , to place ( ie; bring together ) on each “ Face “ , keywords belonging to a given “ Skill “ or “ Function “

·         Goal = Getting all “ same coloured “ keywords ( squares ) onto the same face of the cube

·         Path = Time taken ( shortest )

·         Each “ face “ of our Virtual Rubik Cube , would have same colour , if someone succeeds in virtually “ rotating “ the layers along the 2 AXIS of freedom , until all squares are of SAME COLOUR – meaning that all squares contain Keywords belonging to SAME SKILL

·         We can “ time “ the game , to see which visitor ( WHO ) , manages to get ALL keywords ( squares ) on the SAME face in the shortest possible time ; then give him recognition / credit by publishing his name on our web site

·         This could be a lot of FUN – and could, possibly draw a lot of young kids to our web site ! 


There will be no login / registration for playing the game . Just walk in and play . Then upload the COMPLETED / SUCCESSFUL image ( with time taken ) and email to all friends to prove your cleverness ! [ 06 JAN 2007 ]



Page  69

·         Particles  =  Keywords

·         Space     =  Text Resume

·         Best found solution  =  Resume with highest score

·         Better one  =   Addition / deletion of  “ which “ & “ how many “ keywords , would result in a Raw Score better than the “ best found “ solution / resume ?



Page   70

·         What keywords ( elements ) are always found “ together “ ?



Page  72

·         Is one resume , a “ solution space “ in which particles ( ie; Keywords ) are swarming around ?


Page  91

·         Set of data   =   Master set of 5,000 keywords

·         Smaller set  =   Function-wise sets of 100 keywords

·         Classification  =  “ Skills “ & “ Functions “ are Classifications



Page  92

·         Read my notes on “ Expert Systems “ / eg: finding keywords which have NEVER occurred before in ANY resume  . 


How will software “ Know “ that it is a NEW keyword ?

 – and then know “ to which new Skill / Function “ does it belong to ?


·         Clusters are , Functions / Skills / Cities / Designation Levels / Edu Qualifications / Experience etc

·         Customer Set : Obviously , WIPRO / Infosys / TCS / Satyam , belong to a well-defined “ customer set “

 . They all have “ Common Attributes “ , ie : similar / identical job advts posted / similar / identical , resumes searched



Page  93

·         Each “ sub set “ can be ,

#  same SKILL / same FUNCTION / same CITY / same EDU etc


·         Corporates are “ purchasing “ resumes from job portals and we will have exhaustive data on their “ purchases “ , ie : Number / Type of resumes transferred to folders / opened / viewed




Page    98

·         We are planning a “ Recommendation  System “ – which would recommend job advts to jobseekers and resumes to Recruiters

·         If Wipro HR manager shortlisted / interviewed such and such candidates , same could also be of interest to Infosys HR manager



Page  113

·         A learning component to identify new rules = I have written some rules


Page  118

·         This is what we are interested in. Starting with ( may be ) 50 rules on recruitment ( getting selected / getting appointed ) , we want the algorithm to discover 500 “ NEW RULES



Page  142

·         Can we develop an “ AGENT “ ( ant ) for each corporate subscriber’s each job advt., which travels to “ distant places “ ( different job sites ) , and safely bring back “ food “ ( resumes ) to its own “ nest “ ( folder ) ?

·         Millions of “ ants “ ( software agents ) , let loose on Web Network, each programmed to find a “ specific “ type of resume – then , when it finds , passing on this data to the next ( adjoining ant / agent ), ie; communicating

Then becoming free again to search for next resume for which it is programmed


A resume may pass from one agent to another ( may be several hundred / thousand ) , till it finally gets received by the ANT / AGENT , who is “ programmed “ to find it in the first place !


So , it is not necessary that an AGENT ANT finds only that resume for which it is programmed , as long as it finds any ONE resume , from ANYWHERE & communicates ( passes onto the next / adjacent Ant )


Like Packet Switched Network ?


All packets getting assembled by the DESTINATION ANT


Parameters stored getting matched with arriving resume’s parameters



Page  143

·         In GURU-JEM ( improved version of HARVESTER ) , we are trying to find web records containing Company Name / Designation,

But from a single source ( viz: Google )


Our software agent travels to Google , finds and brings back the results ( food )


But , could we possibly design / devise , millions of software agents , each programmed to roam the Web ( or , predetermined URLs ) and find,


#  One of the thousands of “ designations “ , OR


#  One of the thousands of “ Company Names , OR


#  One of the lakhs of “ Executive Names “ , OR


#  Any combination of the above ,


Then bring back the results ?



·         Since most job sites permit access to  “ Job Advt Database “ to any visitor without need for a Password, it may be much easier for ANT AGENTS to roam job sites ( like Search Engine Spiders ? ) and bring home suitable Job Advts ( what we do in a limited manner )


Page  165

·         Game  =  Online Recruitment / Searching for Employers / Searching for Candidates

·         Characters  =  Recruiters  /  Jobseekers

·         Agents        =  Job  Advts  /  Resumes

·         Environment   =  Virtual Job Fair /  Virtual Employment  Portal



     { On Line  Jobs  Fair  / 




Page  207

·         I believe Cyril used such an algorithm, to read a plain text resume . The software did manage to accurately “ find “ the “ Address “ ( from anywhere in the resume ), after about 72 hours of continuous “ exploring / processing / learning “


This was nearly 8 years ago . I am sure by now , far more powerful neural-net “ Shells “ can be freely downloaded , which would “ parse “ a plain text resume to find accurately, ALL the “ fields / values “ which we need to create a “ Structured Database “


It is simply a question of experimenting and now , we have no shortage of hardware  [  07  JAN  2007  ]



Page   230

·         Someday ( when we have a million resumes on our web site ), we will have many sub-sets of candidates who started their careers ( first job ) ,

          #  at the same AGE , and with


          #  the same EDU QUALIFICATION



         Question is :  How did their careers “ Evolve “ ?


         What Salary / Designation , did each of them reach / achieve , after 5 years / 10
         years / 15 years ?

  

Was there a “ pattern “ ?


         Did their “ career paths “ run “ parallel “ or did they diverge ?


         What other “ factors “ ( eg: Employer Companies ), influenced such divergence ?


         Did some “ plateau out “ after a time whereas others continued to climb the
        Designation / Salary ladder ?  (  Graph drawn  to illustrate the concept )



Page  300

·         With an ever-expanding set of “ Rules “ , it will be possible for a “ Rule-based “ system to detect fake / fudged resumes , where a candidate is telling a lie re: some facts

·         I have listed several such rules . See my notes in “ Expert System “ . Also my handwritten notes in the margin of book , “ EXPERT SYSTEMS “


·         In each resume , each & every field-value is a “ FACT “ . 

Therefore , facts are , Age / Experience / Designation Level / Edu Quali / City / “ Skill Keywords “ found / Salary / Employer Name  etc


·         One can start with simple rules such as

 ,
#  Experience ( years ) cannot exceed Age


#  Age cannot be less than 16


#  Edu Quali cannot be less than 10th Std / SSC


#  MD ( Managing Director ) cannot be less than GM ( General Manager )


#  Post-Grad cannot be less than  Graduate


#  Salary cannot be less than Rs 1000 pm




Page  335

·         In developing Function Profile grphs, we are simply depending on “ presence “ or “ absence “ of any given Keyword ( Binary Status ) . 

Then assigning a “ weightage “ ( of a given amount of weightage of ZERO ) , depending upon present or absent


But in real world, it may turn out that the Candidate with a lower Raw Score ( because of many “ absent “ keywords ) , turns out to be a better choice ( higher interview-score in Interactive Interview Tool ) , than a candidate with a higher Raw Score ( where most Keywords were present )


In such a scenario , should we try out “ Fuzzy Logic Algorithm “?



Page  372

·         Author’s note :   Consider an email program that monitors the behaviour of the user. When e-mail message arrives, the model observes what the user does with the e-mail message and uses this information to learn how to automatically deal with subsequent e mail message


My comments :   Beysian spam filter ? – based on a starting database of “ unwanted “ keywords in the e mail message



Page  376

·         We must experiment with Kurzweil’s Paraphrasing Software

·         Could Kurzweil’s “ Paraphrasing Software “ be based on this ? See web site of Kurzweil . 

Using this can we “ re-write “ a resume ( lilke creating a step brother ), from a given “ Sample Resume “ ?


If such “ paraphrasing / re-writing “ of resumes can be done online ( automatically )  on our web site , then we could add one more element of FUN – even if the re-written resume contains some absurd text ! In fact , such “ absurdity “ may lend an element of FUN !  [  07  JAN  2007
  ]



Page  385

·         If we succeed in paraphrasing / re-writing a text resume online, we could also generate / develop a “ Subliminal / Subconscious “ function profile graph ! ( - since keywords would have got changed ) . This could be fantastic !



Page  388


·         Eg : Agents of Jobseekers negotiating Salary / Terms etc with Agents of Recruiters


·         Virtual Job Fair  will be / can be a “  Negotiating Platform “   for 
,
#  Buyers’ Agents  ( Recruiters )

#  Sellers’ Agents  ( Jobseekers )





Page  389

·         Only yesterday we discussed that in “ Post Jobs “ form ,recruiter will add,

    #  Put in my folder, all future/incoming resumes having percentile score of > xyz 


    Now he has created an AGENT which checks incoming resumes daily & puts into folder “ Resumes of Interest “ – also an email will go out to the recruiter concerned ( alert )



Page  440

·         A few weeks back , there was a report of a mechanical spider-legged robot , which learned on its own to change its “ gait “ when one of the legs was broken !



   
24  June  2017


www.hemenparekh.in / blogs            

No comments:

Post a Comment