Should I Market my College?

Colleges and universities compete with each other to attract the best students to join them.  Student is making a choice among several options available to her, whether a college decides to participate in this competition or not. And that choice is dependent on the information available to the student, about perceptions that other influencers have about the college brand, and about the guidance student receives from these influencers.

Every student aspires to join the best college, yet their choice depends on what is available to them or what is known to them. Decision making happens in two months period of constant see-saw between what is student’s aspiration and what is available.

What is Available
Not every student can join PGDM program of IIM Ahmedabad. Not every course or every college is available to students, it depends on their academic track record, exam results and performance in the selection process. CAT (Common Admission Test) results are announced well before final admissions, however, that is followed by Group Discussions and Interviews which continue till June-July. Final admission (admits) information is available only in June and July or later.

JEE Main results (Joint Entrance Examination - for B.Tech courses) are announced in April and May. That's the peak of admission season. Until the time of results announcement, student and parents know little about what is available to them. In fact, even this is hard to know because each state has different counselling for different state level colleges (for example, Joint Admission Counselling JAC in Delhi), besides the national level counselling JOSAA.  And these counselling sessions are spread over 6 to 8 weeks with 6-7 rounds and with each round what is available and what is not available is changing.

A student can refer to previous years cut off data, ranking, college reviews, refer to friends and seek help from alumni etc. to make a decision regarding course and college. However, this process is challenging because of a very short period time window available for decision making.

Few Elements of Differentiation
The biggest reason for confusion among students is that there is little differentiation among colleges. Over the last few years, I have personally seen students struggling to chose one NIT over another NIT or a new age IIT or a private engineering college.   The challenge for new age colleges is to define their charter in unique manner and constantly innovate to differentiate themselves.

Aspirations and Affordability
Education is seen as path to better future. And investment in education continues to be very high. India is a growing economy with increase in payment capacity of students. At the same time, parental support continues to remain high when it comes to funding education. With improving affordability, students are also opting for more private colleges. In aggregate, student and alumni reviews across colleges suggest that private colleges tend to have better quality of infrastructure and among the top private colleges, there is better engagement with industry and also more opportunities for industrial training.

Awareness before Positive Brand Association

It is important for any college to ensure that student at least is aware about the college. That's the first challenge- making it to the consideration set. And awareness that is associated with positive attributes which helps the student make the right decision. If a college attracts good students (and maintains good faculty and course curriculum), industrial placements are likely to be better. With improving reputation, it starts attracting a higher calibre of students and faculty, and then it becomes a virtuous cycle. 

InfoEdge Merit Awards - Congratulations Naukri Data Science Team

Congratulations to the Naukri Data Science team. InfoEdge Merit Awards for "Improvements in Naukri Search and Matching Engines over the year".

"Search and matching engines are core to Naukri experience for both jobseekers and recruiters. Over the last few years, we have seen a phenomenal improvement through semantic search and better quality recommendations.  Jobseeker experience is now personalized with new contextual autocomplete and suggestors improving the quality of search criteria entered. Semantic search and personalization deliver better discovery and more relevance jobs. Jobseeker feedback about relevance of job alerts has improved from 60% in 2014 to 76% in 2016 and is at present close to 80%. In addition, new job recommendation algorithms – Jobs Applied by Similar Profiles (JASP) and Online Recommendations have been a phenomenal success and brought additional incremental traffic to Naukri. Recommendations are now responsible for 80% of all applies on Naukri and are key driver of user growth in Naukri.  On the recruiter side, semantic search has improved the experience of recruiters and improved the discovery of relevant CVs. Apply Relevance Score has received very positive reviews from recruiters. Today, we don’t send 20% of the applies received as an individual mail. Delete Job Survey from recruiters  has shown a 20% improvement largely because of Apply Relevance Score."

Congratulations to all past and present members of the Naukri Data Science team.

- Vivek Jain

AI in Recruitment : Scoring Applies in terms of Relevance to a Job

Naukri Apply Relevance Score provides an indicator of how relevant an apply is to the job which a recruiter has posted on Naukri.com.  Recruiter receive this score as part of the subject line of the apply mail that is sent after jobseeker applies to the job on the site. Only highly relevant CVs are rated as 5star or *****, while 1 star * applies are the least relevant basis the parameters of the job and the jobseeker profile and resume.

Recruiters can chose to receive applies only above a particular rating and hence spend more time on higher rated applies. Based on the results we have gathered, a 5 star ***** rated apply is 2 times more likely to be viewed and shortlisted compared to a 2 star ** apply.

28th March 2018 Update - Major improvement done by the Naukri data science team, a 5 Star ***** rated apply is now 12 times more like to be viewed and shortlisted compared to an average apply. 

- Vivek Jain

Please also see my blog post on (1) AI in Recruitment - Understanding Skills and Designations, (2) Story of Naukri Job Alerts, (3) AI in Recruitment - Do Job Descriptions Represent the Intent of the Recruiter?, (4) AI in Recruitment - Is Mumbai closer to Delhi than Agra?, and (5) AI in Recruitment - Word2Vec Opens Up New Possibilities

Celebrating new milestone of Naukri Job search App on Android- rating of 4.5

Congratulations to the entire Naukri Team, Naukri Jobseeker Android App crossed the average rating of 4.5. 

Digital Marketing – Landing Page Optimization Must for Each Source

A large amount of marketing money is spent on brand building as well as performance marketing (generation of incoming traffic of customers). Marketing outreach through mass market, conference participations, email marketing or digital media brings curious as well as high intent traffic. Digital media enables very fine monitoring of campaigns and their performance optimization to ensure higher online conversions and revenue.

Customer Segment and Context of Each Source is Different

The intent of the customer depends on the source. Each source represents potentially a different customer segment, with its own differing context. Hence, multiple campaigns landing on the same page, even when the ad copy is same, can lead to different conversions. For example, one source may bring broad based audience with customers having higher propensity to pay, while another source may bring niche set of customers which are strategically important yet not willing to pay a lot.

Tracking Each Source is Important

Sources are often added or deleted in a running business. An experimental campaign without a change in landing page with a very short turnaround time helps in gauging the effectiveness of a new source. However, it is better to track a campaign separately with a tracking parameter rather than use pre and post-performance of the landing page.

Different Campaign Sources Have Different Conversions

Single Landing Page vs. Multiple Landing Pages

While a single landing page helps in managing the customer communications better. There is only one set of content to review and ensure nothing is wrong. Also, each landing page now needs two variants – desktop and mobile. Multiple landing pages helps in optimizing each page for specific campaign. However, if the landing pages don’t differ a lot, source specific customization of a single landing page may be better from content management perspective.

Comparing a New Source with an Existing Campaign

A landing page optimized for an existing campaign when deployed for a new campaign may not truly measure the effectiveness of the new source. Only when the landing page has been optimized for the new source, it makes sense to reach a judgment on the new source.  For example, niche set of customers may have a specific need and if the landing page does not reinforce their needs and wants, conversions may remain poor. And we may wrongly attribute to the payment capacity of the audience from the new source, while the culprit lies with the communication on the landing page.

AI in Recruitment: Word2Vec Opens up Interesting Possibilities

CVs and jobs are text heavy and like all the challenges which exist with natural language – multiple ways of describing the same concept, ambiguity, synonyms etc.  Meaningful interpretation of text requires extracting this knowledge in a machine understandable form. Among others similar problems exist in speech recognition, machine translation and conversational systems like Siri.

AI systems that process images work on high dimensional vector representation for each pixel embedded in a two-dimensional image. Most of the information needed to recognise images is present in the two-dimensional vectors.  However, most text processing system use a “bag of words” representation of text, that is each word is represented by a ID. For example, Infosys and TCS may be represented as say, ID75698 and ID 98603. And don’t use the contextual relationship between the two words, which otherwise recruiters or jobseekers can understand and process.

Latent Semantic Analysis is a technique which condenses the statistical count of co-occurring words into topics or concepts. It has been shown that Latent Semantic Analysis would recognise a shallow kind of topical similarity and not work well where subtle semantic relationship between words is present.

In contrast, predictive methods like Word2Vec learn the function that captures the salient statistical characteristics of the distribution of sequence of words. The function can associate each word with a continuous-valued vector representation that corresponds to a point in a feature space.

Word2Vec takes raw text as an input and the training of the Word2Vec model (skip-gram) is to arrive at vector representations of words that best predict a window of surrounding words. One can imagine that each dimension of that space corresponds to a semantic or grammatical characteristic of words.

The hope is that similar words get to be closer to each other in that space- that is we may expect Infosys Technologies and TCS as companies to be much closer to each in this feature space. That opens up new possibilities for AI in recruitment.

To Learn more on Word2Vec - Please see Getting Started with Word2Vec

- Vivek Jain

Please also see my blog post on (1) AI in Recruitment - Understanding Skills and Designations, (2) Story of Naukri Job Alerts, (3) AI in Recruitment - Do Job Descriptions Represent the Intent of the Recruiter?  and (4) AI in Recruitment - Is Mumbai closer to Delhi than Agra?

Naukri.com featured as an important case study in KrantiNation

Naukri.com has been featured as an important case study in KrantiNation for using Machine Learning. According to the book author Pranjal Sharma, Machine Learning is a key technology for the 4th Industrial Revolution.

For more details on the book, please see KrantiNation: India and the Fourth Industrial Revolution