Measuring and Improving Software Recruiters’ Performance

Every thought leader after Deming has extolled the virtue of measuring whatever we need to improve. I recently read this article  – it suggests seven metrics to measure a recruiter’s performance. Many more articles and suggestions for building performance scorecards are published. We need some simple metrics that could be quickly ascertained without investing in specialized software etc. In this article we are exploring two such metrics to measure software recruiters’ performance and ways of improving the same. By definition a software recruiter specializes in hiring software professionals.

In this post we will focus on the recruitment process including recruiters, hiring managers, other members of the interview panels, recruitment consultants and agencies and candidates. Combined effect of their individual behaviors results in the inefficiencies of the recruitment process.

TallClaims

Here are some typical characteristics of the software job-seekers’ market. Candidates often claim a lot more in their resumes than their real “hands-on experience”. Recruiters – particularly those who are experts at Boolean search rely a lot on what is claimed in the resume and base their search on keywords and extrapolate an individual’s capabilities based on the companies worked for and the schools attended. The best way to separate substance from hype is by having a short telephonic conversation. Just a few questions would have the candidate himself telling where his or her real strengths are and what should be ignored.

Spray&Pray

At this stage let us introduce two metrics to measure the efficiency of a source such as a recruiter or an agency providing candidates.

Recall of a source measures its reliability or spread of coverage of the the total population of suitable candidates. This is tough to measure as we don’t know the “total population” of suitable candidates who are currently looking for a change. As a proxy we can replace the “total population” with “total known number” by adding number of suitable candidates sourced from all sources including employee referrals, direct applicants, agencies and recruiters.

Precision of a source measures how many suitable candidates were sourced as a percentage of the total number of candidates sourced. This shows what percentage of the sourced candidates were useful and what percentage of the sourcing effort resulted in “waste”. This is measured easily by taking a ratio of candidates who are found worthy of second interview over total number of resumes coming from the source.

Candidates sourced but not found suitable are called false positives – our effort on interviewing these candidates is wasted and needs to be minimized. Similarly candidates who were suitable but were not sourced are called false negatives– indicating lower reliability of the source in terms of its ability to find suitable resources.

The main reason for false positives is due to the fact that many recruiters and agencies are singularly focused on improving recall. Their intent is to improve the probability of finding a match by sourcing as many resumes as possible. This “spray and pray “approach results in a lot of wasted effort in interviewing false positives.

TelephonicRound

On the contrary if a recruiter applies a filter and reduces the total number sourced by having a preliminary telephonic round , it will reduce false negatives and improve precision. An upside of this approach results in a better deal for the hiring managers who have less interviewing but better results.

Majority of hiring managers believe that recruiters can’t really do any technical screening. Recruiters do “keyword” based search – not really going deeper to find out if the candidate really has the relevant technical skills. This results in a communication gap between the recruiters and the hiring managers. Hiring managers don’t think that feedback any more detailed than “Technically Unsuitable” would be understood by the recruiters.

We believe that recruiters can be trained to do preliminary technical screening. Some amount of guidance in the form of technical questions that weed out obviously unsuitable candidates can improve the recruiters’ ability to judge.

SmallBatches

If we have more meaningful feedback coming more frequently; it will improve the precision and reduce wasted effort and interviewing fatigue. Smaller batch sizes would help get early feedback resulting in corrective action of improved technical filtering. Baby steps of small batches each one improving precision in an iterative way seems like the way we should hire technical talent.

 

 

Dos and Don’ts of Lean Startup- Top Takeaways from The Lean Startup Conference 2014

Lean Startup Conference 2014

Lean Startup Conference 2014

Main Takeaway- Continuous Experimentation Well Beyond The Startup Stage

Contrary to the generally held belief that lean startup principles advice experiments in early stages of a startup; many speakers at the conference showed how they are experimenting continuously at all stages of their ventures.

Eric Ries in said that “Product market fit and experimentation is not a one time activity. It’s a continuous flow of activities. There are no discrete big jumps! Think of these steps in continuous flow that lend themselves to go back if an experiment fails”

Hiten Shah of Kissmetrics reiterated that a meaningful metric leads to a hypothesis and then to an experiment to validate it. Startups should always be A/B testing. Empirically 1 out of 5 tests succeed. Strive to win 1.67 out of 5.

A/B testing can help not only at different stages of a startup; but also for various activities including website traffic, app installs, welcome emails, Web/Mobile onboarding, E-mail digests, Triggered notifications, dormant/churned users.

Des Traynor also said that having continuous feedback is more valuable than one time event driven feedback.

Experiments helped even established brands like Rally, Google and Vox Media to validate hypotheses at later stages of their product lifecycle

  • Rally launched a dummy brand waffle.io targeted towards developers to protect the parent brand from the impressions created by the experiments. Finally Rally decided to have both brands.
  • Google Adsenses team validated Partner Problems using Lean Startup Principles. Blair Beverly said that they faced problem with new projects scaling too early and failing as they lacked historical data to go by. He got coworkers at Google ad senses team to use the Lean Startup. They scheduled office time to read the book, being helpful and not pushy. They also gave them a reading guide with questions. In the end they identified three hypotheses; put together templates like the partner problem hypothesis. People felt good about invalidating their own hypotheses as it saved them work that would’ve been wasted.
  •  Vox Media launched Vox.com in 9 weeks using analytics to guide customer validation. Melissa Bell got her co founders and others from Vox media in the same room to get everyone on the same page about her vision. Many editorial staff came from Washington Post whereas Vox was an agile technology company. They used card stacks for flexibility. They had problems with the way editors used card stacks, as it was difficult to navigate-hence they analytics were used to solve the problem. Now Vox.com has 22m users. Delivering content to users where they are-on social channels such as Facebook or YouTube instead of own URL.

Lean Startup- Dos & Don’ts

Max Ventilla

  • Pivoting statistics- 80% of failures didn’t pivot, 65% of successes Pivoted but 85% of Huge Successes (>$1B exit) didn’t pivot. Those didn’t pivot felt that evolution is safer than betting on intelligent design.
  • You need to eat your own dog food. Use your product to solve your own problems. If not you are at an enormous disadvantage.
  • Invert the org chart :customers & customer facing team should be on top. They should be heard and not told what to do.
  • Force yourself to pretend at the earliest possible moment what you want to be- to learn whether its worth being what you want to be. Landing pages, Concierge or Wizard of Oz are ways to pretend.
  • Don’t speed up for the sake of it. For startups not going fast enough is not the main risk. False summit is the reality. Journey of a startup is slow like that of a mountaineer. A new goal appears once you have reached what seemed like the ultimate goal.

Grace Ng

  • According to Grace Ng success criterion for any experiment is the weakest outcome that will give you enough confidence to move forward.
  • Testing the riskiest assumption on buy side in a two-sided market place could be deceptive in a sellers’ market. Sellers may not automatically follow even if you find many buyers.
  • Validated hypothesis doesn’t necessarily lead to a viable business. Grace Ng tested a hypothesis whether birdwatchers will post photos to ask questions. The Hypothesis was valid but the problem turned out to be too small – not a big pain-point.
  • Don’t validate the solution before validating the problem. As in the case above; the problem was not big enough though the solution was right.

Eric Ries

  • When it takes too long to learn as end results take time, use proxy metric like number of likes or start a cohort.
  • Don’t depend on one experiment to determine the product market fit. Keep testing and validating along the way as you grow. Growing too fast by taking product-market fit for granted is dangerous.
  • Don’t get misled by corporate America’s habit to underinvest or overinvest. “All Hands On Deck” sounds great but surely is a sign of overenthusiasm.
  • Avoid handing off innovation between silos. Handoffs kill innovation. What is learnt in one silo can’t be handed off to another silo.
  • Don’t add features for the sake of it. Its better to err on the side of being too minimal to get early feedback and learning. Its easy to add a missing feature later.
  • Pay more attention to paid users’ feedback than free users’ feedback. Free users ask for more; paid users ask for better.
  • Don’t use vanity metrics- Eric’s law: At any time no matter how badly you are doing there is at least one Google analytic graph that’s up into the right

Joanne Molesky

  • As you go through build-measure-learn cycles for product the same way you should be going thru build-measure-learn cycles for process compliance.
  • Beware of developers’ tendency to focus on how to do things than on outcomes. Developers tend to ignore security as they are dazzled by technology, so they focus on doing things faster-not safer. Security testing, threat model and risk metrics should be included right from the beginning and not at the end.

Dan Milstein

  • Don’t take idle pleasantries as positive feedback. People tend to be polite and cordial even though they are least interested.
  • Don’t choose to see what fits in a narrative that sounds good and makes you look awesome. That is self-deception. Realize that a startup is a series of unpleasant encounters with reality.
  • Don’t own a plan. Own questions. Plans will change.

Hiten Shah

  • Test small changes- Google sign on and changes to verbiage improved acquisition by 314% for KissMetrics.

Brant Cooper

  • Don’t as two questions that kill breakthrough innovation – what is the roi? When do we get it? In order to answer these questions we have to look at existing markets which kills innovation -innovator’s dilemma. We need to build cultures or safety net for innovators.

Conclusion

Most of the takeaways and dos and don’ts are common sense for any practicing entrepreneur. According to Eric Ries The Lean Startup process is more widely practiced than talked about. Most entrepreneurs are agents of long term change. They don’t think The Lean Startup is a big deal. As with most profound thoughts- it seems obvious after its well thought through, well organized and well presented.

Top Takeaways from Nasscom Product Conclave 2014

Insights into startup ecosystems of the US and Israel

Technoratti of India descended to Bangalore for the annual Nasscom Product Conclave 2014 on 30th and 31st October. Here are some top takeaways from the conference with a few from the Pune Connect event that happened on 8th Nov.

New startups are being launched at a feverish pace in India. India has 3100 startups-taking it to # 3 ahead of Israel which has only 1000 . Technologies and infrastructure to build software products have become available and the domestic market has grown to become significant enough to take note. Devices at the edge and powerful technologies at the back end are throwing up unprecedented opportunities for startups to innovate. App to App communication is exceeding browsing traffic. John McIntyre and Zack Weisfeld presented the evolution of startup ecosystems in the Silicon Valley and Israel.

Startup EcosystemStartup Ecosystem

Startup Ecosystem

Strong universities which acted like feeders and presence of prominent MNCs provided the infrastructure needed for healthy startups in Israel. Few initial successes provided the much needed boost for the startup activity to take off. Military spending and a lenient tax regime by the Government helped. The Israel Government also promoted VCs and provided exit routes.

History of Silicon valley is similar in the role played by the US Government, world war II and electronic warfare research at MIT, Harvard and Stanford. John McIntyre said that Silicon Valley is a state of mind. “Free flow of people and ideas is natural. The team you build is more important than the idea itself. There is no stigma attached to failure- you have to fail and reinvent to finally succeed. Innovation happens when you address customer desire in a financially viable product that is technically feasible. Silicon valley is a melting pot where the magic happens because of diversity of people.”

India is following the footsteps of these countries by starting a Government funded innovation -the Aadhar card program. 700 million cards were issued in 4 years with a team of 20+ developers. Aadhar has developed an API for authentication and KYC (Know Your Customer) which is being consumed by about 500 independent developers. The Aadhar team showed some innovations that will drive the future roadmap. One of them developed at the MIT media labs was an app that does iris scans using 1.2 megapixel camera and retina display available in some mobile phones today. Soon Aadhar could make one click two factor authentication (like ApplePay) possible in rural India!

Like Appstore and Google Play there are many other platforms like Salesforce, Facebook, LinkedIn and Azure that have their own ecosystem of apps. Aadhar could become one such ecosystem.

Dhiraj Rajaram of Mu Sigma cautioned that we shouldn’t get carried away by the hype associated with product startups and seriously look at services. Services can dynamically provide solutions on the fly to problems as they arise whereas static products solve specific problems they are meant to solve. Tarken Maner also pointed our that out of $3.1 trillion global IT market only $1200 billion is accounted for by hardware and software products- balance $1.9 trillion is accounted for by services.

Tips on business and marketing

Business applications want to abstract trust broking to aggregators of services like Ola Cabs or Flipkart . Promod Haque said that App to App communication is exceeding browsing traffic. As users are demanding mobile first ; some applications are moving to mobile only. Zomato scrapped their web interface,built a mobile only app and then moved to build desktop app after 6 months. Omnichannel seems to be catching up – it not only accounts for various form factors but integrates digital and physical channels of conducting business. Users get a seamless experience across multiple channels – they can start in a new channel from where they left in an old channel. Tarken Maner said that you can strategically use channel to differentiate just the way you traditionally used customer profile or product features to differentiate. B.V.Jagdeesh said as business applications are starting to look more like consumer apps;  B2B market provides more opportunities than B2C. Once you acquire 20 customers in the B2B market you are safe to start building your business on that foundation. Though B2C appears more attractive ; sustainable customer acquisition in large numbers makes it more difficult.

Dhaval Patel of Kissmetrics described how their company scaled its outbound marketing communication. He said that they focused on low cost channels like Twitter and stayed away from paid conversions. They focused on creating content that their customers loved. He advised startups to join professional groups on social media like LinkedIn to study others’ content including competitors’ content and add a new twist to put across a different point of view. Once the content is up the same can be pumped up first by e-mail and then by social media campaigns. Both e-mail and social media are complimentary tools and need to be used in conjunction.

Campaigns need to be measured by studying sharing and social engagement metrics . Qualaroo is a great tool to ask questions to visitors. Vanity metrics can kill ROI . Metrics become meaningful only when they reach high thousands. Kissmetrics published over 50 info graphics and received more than 20k comments. Info graphics get hundreds of shares on LinkedIn, FB  and Twitter.

Dhaval advised startups to ” Treat content creation as customer service. Measure and optimize your content. Do a/b testing , stick to a regular schedule to publish content. Images are very important for content to make people click. Create content that teaches. Blogs are cost effective e.g.Kissmetrics’ cost per sign up is as low as $7. Always position top content in left panel so that it’s easy to find.”

Product Tips

Aakrit Vaish  co-founder of Haptik Inc said that mobile first is not just a business strategy but it changes the way we build and use applications. He said that everyone at Haptik uses low bandwidth 2g connection so that they can live the user experience of an average user. He said one should use mobile web if the use case starts in the browser e.g. with Google search- this way the user can reach your application in 1 click instead of 6 needed to download and install an app. Building an app would make more sense if one were leveraging native capabilities like geo-location or push notification. He said users download and install a number of free apps which they eventually delete.

Omni-channel means unification of web, mobile and in store experience- any user switching channels starts where he left off. Lowe’s – essentially a brick and mortar company now offers omni-channel experience to its customers. Associates who walk the floors of Lowe’s stores can capture the conversations about all the products and share it so that information is not lost. Product locator kiosks placed at prominent locations in the stores give stock position. Lowes planned ahead for iOS-8 and launched touch Id. They armed their associates with 42000 mobile phones not only for better operations but for better connection with customers. With more than 500K products online Lowe’s is a good example of digital-physical blur. Tesla is another example of digital-physical blur. Its more software than car.

Ramesh Raskar of MIT Media Labs shared his advice on how to invent. He explained it with his idea hexagon with some examples. The hexagon has a question at the center – “Given X whats next?” and the 6 corners show ways of inventing based on current state X.

Idea Hexagon

Idea Hexagon

  1. Xd– Add a new dimension. E.g. if Flickr shared photos.Youtube shares videos.
  2. X+Y. Pair X with Y – more dissimilar Y would be better. E.g. Retina display for eye checkup
  3. Xv – Given a hammer get all nails. E.g. Use mobile phone as a camera.
  4. ~X- Do exactly the opposite. E.g. reverse auction, toll free calls.
  5. X++- Add an adjective like faster, cheaper, cooler, more democratic to X. E.g. Skype for cheaper international calls.
  6. X^- Given a nail get all hammers – E.g. LensBricks- appstore for cameras.

Tips on culture

 Employees are demanding enterprises to provide more freedom. InMobi has given this freedom to bring about a cultural change in their company. They have stopped using traditional way of hiring – now they follow Hiring 2.0 to hire the best teams in hackathons conducted by them. Employees built their office to suit their liking instead of the standard cubicles.

Naveen Tewari said that “You can get 100X the valuation if you get the culture right. Culture is proving to be the disruptive differentiator.” He defined culture as experiences that the company gives to its customers and employees. Change, innovation, fast failure and learning ,fast iterative growth are difficult to implement without the right culture. InMobi has implemented an open door policy for employees who could leave to do their own startup and come back if they failed. They focused on growing instead of managing people. They did away with the performance appraisal system. Connecting with families including grandparents and also with ex-employees built the company’s soul.

Jim Ehrhart repeated what was said in an earlier post – boundaries of enterprises are blurring as we move from workforce to crowdsourcing. IT barely have the tight grip on what people do as they used to have. Employees want to use apps for everything they do. Many enterprises are planning to build their own enterprise appstore.

LeanRounds Instead of Seed Rounds for Early Stage Startups

Seed Vs Lean Rounds

Seed Vs Lean Rounds

In an earlier post we saw how the lean startup principles can scale an idea. However we are facing resistance to the concept on account of prior commitments. My company ‘s services are commissioned to build quality products but there is a tendency to “stay in the building”. Promoters and investors decide to walk along a certain path and there is no room for course correction. In fact investors might treat any deviation from the business plan as a breach of contract. Investors are wary of entrepreneurs frittering away the invested funds on activities other than the business plan. This is contrary to the lean startup method of doing course correction based on continuous market feedback and hypothesis validation.

The traditional seed investors generally review the progress of the portfolio ventures on quarterly basis. The startup is required to stay committed to execute the business plan. In fact the term-sheets often mandate that startups use the invested funds only to execute the business plan. This arrangement is often counterproductive in business environment which is becoming increasingly volatile, uncertain, complex and ambiguous (VUCA). Frequent customer feedback needs to be taken. Startup needs to change its direction based on market feedback. With no feedback startups often miss early warnings of impending failure. Promoters love staying focused on the business plan that embodies their dreams. Often no feedback is sought and unsolicited feedback that doesn’t resonate is ignored. These circumstances result in startups deploying resources and building momentum much before they have valid reasons to do so. Startups need to be more responsive, agile and lean.

More than a decade ago our startup received seed funding from StarTech. We received the seed round with a rider that we use the invested money and our energies only to build the product as per the business plan. Halfway through the process we realized what we were attempting was too big. We would have been better off building something much smaller. However we continued executing the business plan – just hoping against hope that luck would bring some customers to pay for a product that wasn’t even 10% ready. As expected we ran out of money before we could sign up any customers. Had we done some course correction and opted to build something smaller we might have had a better chance. But we had our marching orders which didn’t allow us to think of any other approach.

Ten years later the tables have turned. As a successful entrepreneur I along with a few angel inestors have launched a fund called LeanRounds. This post explains the guiding principles of LeanRounds.

Harsh Reality of startups is that nine out of ten startups fail in the first year itself! The main reason for this failure is lack of mentorship and investments. LeanRounds plans to provide these two essential inputs to selected early stage startups. We don’t plan to invest in business plans. We would rather invest in assumptions or hypotheses that need to be validated. The central idea is to fail early and learn from the failure. We still have a lot of runway left even if nine out of ten hypotheses turn out to be invalid. These experiments carried out to validate the hypotheses would cost very less and would not run longer than a couple of weeks. Depending on whether the hypothesis is valid or not, the investor and the startup may decide to continue along the chosen path or change the direction or drop the idea.

As an investment fund; LeanRounds would divide its risk over many units in its portfolio. Each unit is not a startup with a business plan, but a falsifiable hypothesis. Instead of investing in a dozen or so startups; LeanRounds plans to invest in hundreds of hypotheses. Traditional seed stage investment decisions are based more on the credibility of promoters and their track record than the business idea itself. This is one way the investors try to reduce their risk. However they tend to ignore many promising business ideas from teams without any credible track record.

Baby steps instead of long strides

Baby Steps Vs Long Strides

Baby Steps Vs Long Strides

There was some value associated with startups staying on course and committing all their energy and time to a mutually agreed business plan. In fact as we saw earlier some term-sheets mandate that the invested funds be spent on the business plan and entrepreneurs were discouraged from using these funds for experimenting with other ideas. This way of working served its purpose in relatively stable business environments of yesteryears.

The business environment is constantly changing. The assumptions that are valid today won’t remain so for long. LeanRounds believes in frequently validating hypotheses. We advise startups to build products in agile iterations. Each iteration lasts only for a couple of weeks. Startups should seek market feedback and validate their assumptions at the end of every iteration. They should avoid long development cycles as it distances them from market feedback. Each iteration has a falsifiable hypothesis to be validated. It could be an assumption that customers will behave in a certain way. While it may turn out that the customers behave entirely differently thus falsifying the initial assumption but resulting in new insights and learning that could help to formulate the next hypothesis.

Does this mean that entrepreneurs will fritter away their time and money experimenting with various ideas? That would obviously not happen because LeanRounds invests in hypotheses that are worth testing. Each round of investment comes with some advice that the entrepreneurs need to follow. We also ensure that chosen teams have the needed experience, skills and ability to execute the business idea should the hypothesis turn out to be valid.

Lifecycle of Startups in LeanRounds Portfolio

StartupLifeCycle

Startup LifeCycle

As it might have become clear by now; startups have to continuously form and validate hypotheses. These may be short experiments lasting a couple of weeks in the initial stages of the lifecycle. However once the startup has passed through the initial filters of problem-solution validation; further hypotheses and validations might need longer running experiments. To illustrate this point we have identified seven hypotheses that typically represent seven stages in the lifecycle of a startup. Some finite number of startups will get filtered out at each stage of the lifecycle. The hypotheses grow in time and money needed to validate them as you progress through these stages.

More Details About LeanRounds Investment and Exit

Investment Ladder

Investment Ladder

LeanRounds investments start small and grow as a startup validates its basic assumptions and moves to validate bigger assumptions. Initially a startup needs to validate if the problem they are trying to solve is worth solving. This can be done by using very low cost methods like landing pages. Later we need to build a MVP or prototype and test it in the real market which needs higher investment.

Along with investment comes some advice from experienced entrepreneurs who’ve been there and done that. This advice helps the startup to accelerate its value ten-folds in very short – lean and agile sprints.

The value of startups multiplies in orders of magnitude as they move up the ladder shown in the diagram above. We believe that a credible team focused on solving a problem that is validated to be worth solving is an order of magnitude more valuable than one that does not know whether the problem that they are attempting to solve is hurting enough customers to have them pay for having it solved. In the same vein a startup that is further along by having a validated solution that’s better than the existing solutions for customers to switch is an order of magnitude more valuable.

The investments are linked to hypotheses being validated. At each stage the experiments become more demanding and cost more. A prototype might cost ten times as much as a landing page and version 1.0 of the product might be 10 times more costly as compared to the prototype.

Bigger investors take interest as the startup climbs the ladder. The mortality rate is highest in the fist two stages of the lifecycle and the investments are too small to attract any investor. These are the times when a startup can turn to LeanRounds instead of bootstrapping or going to friends and family to raise the money. LeanRounds plans to exit once the startup is at a stage in the lifecycle where bigger angel investors and private equity firms start showing interest.

Resume Ranking using Machine Learning- Implementation.

In an earlier posting we saw how ranking resumes can save a lot of time spent by recruiters and hiring managers in the recruitment process. We also saw that it lends itself well to lean hiring by enabling selection of small batch sizes.

Experiment – Manually Ranking Resumes

We had developed a game for ranking resumes by comparing pairs with some reward for the winner. The game didn’t find the level of acceptance we were expecting it to find. So we thought of getting the ranking done by a human expert. It took half a day for an experienced recruiter to rank 35 resumes. Very often the recruiter asked which attribute was to be given higher weightage? Was it experience or location or communication or compensation?

These questions indicate that every time we judge a candidate by his resume; we assign some weightage to various profile attributes like experience, expected compensation, possible start date etc. Every job opening has its own set of weightages which are implicitly assigned as we try to compare the attributes of a resume with the requirements of the job opening.

So the resume ranking problem essentially reduces to find the weightages for each one the attributes.

Challenge – Training Set for standard ranking algorithms.

There are many algorithms to solve the ranking problem. Most of the ranking algorithms fall under the class of “Supervised Learning” which would need a training set consisting of resumes graded by an expert. As we saw earlier this task is quite difficult as the grade will not only depend on the candidate profile but also on the job requirements. Moreover we can’t afford the luxury of a human expert training the algorithm for every job opening. We have to use data that is easily available without additional efforts. We do have some data of every job opening as hiring managers screen resumes and select some for interview. Its easy to extract this data from any ATS (Applicant Tracking System) . Hence we decided to use “Logistic Regression” that predicts the probability of a candidate being shortlisted based on the available data.

We have seen that “Logistic Regression” forecasts the probability based on weightages for various attributes learned from which resumes were shortlisted or rejected in the past. This probability in our case would indicate if the candidate is suitable or not. We would use this number to rank candidates in descending order of suitability.

Available Data

In our company we had access to data of the following 13 attributes for about 3000 candidates that were screened for about 100 openings over the last 6 months.

1)Current Compensation, 2)Expected Compensation, 3)Education, 4)Specialization, 5)Location , 6)Earliest Start Date, 7)Total Experience, 8)Relevant Experience, 9)Communication, 10)Current Employer, 11)Stability , 12)Education Gap and 13)Work Gap.

We needed to quantify some of these attributes like education, stability , communication etc. We applied our own judgment and converted the textual data to numbers.

Data Cleaning

We were unsure whether we will get consistent results as we were falling short of historical data of resumes. We ignored openings that were barely having 10 or less resumes screened. On the other hand we also discovered a problem with large training sets – particularly in the case of job openings that drag and remain open for long. These job openings are likely to have had change of requirements. As we learned later; consistent accuracy was obtained for job openings having training sets whose population was in the range of 40 to 80 resumes.

Running Logistic Regression

We had listed 22 openings for which several hundred resumes were presented to the hiring managers in the last 6 months. We have record of interviews scheduled based on suitability of the resumes. We decided to use 75% of the available data to train (Training Set) and 25% to test (Test Set) our model. The program was written to produce the following output-

  • Vector of weightages for each one of the 13 attributes
  • Prediction whether the set of test cases would be “Suitable” or “Unsuitable”

The result was based on how accurate was the prediction Accuracy is defined as

Accuracy = (True Positives + True Negatives)/ (Total # of resumes in the Test Set)

Where “True Positives” is the number of suitable resumes correctly predicted to be suitable. Similarly “True Negatives” are the number of unsuitable resumes predicted as such. We achieved average accuracy of 80% ranging from 67% to 95%.

Efforts to improve accuracy

Pay Vs Experience -Plot of Suitable Candidates

Plot of suitable and unsuitable resumes on Experience vs Pay didn’t show any consistent pattern. The suitable resumes tended to be more of highly paid individuals who had lower experience. Which is kind of counterintuitive. Other than this the suitable resumes tended to cluster closer to the center of the graph as compared to the unsuitable ones.

Given the nature of the plot the decision boundary would be non linear- probably a quadratic or higher degree polynomial. We decided to test using a 6th degree polynomial – thus creating 28 attributes from 2 main attributes – viz. experience and pay. We ran the program again this time with these 28 sixth degree polynomial and remaining 11 attributes thus a total of 39 attributes. This improved the accuracy from 80% to 88%. We achieved 100% accuracy for 4 job openings.

Regularization had no impact on accuracy. Hence we didn’t use any cross validation set for testing various values of the regularization parameter.

Values of weightages or parameters varied slightly every time we ran to find the minimum of the cost function. Which indicates that the model found a new minimum in the same vicinity every time we ran the program with no changes to the training set data.

Some Observations

Varying Weightages for Candidate Profile Attributes

If you take a close look at the chart above ; we observe the following-

  • One job opening gives extremely negative weightage to “Current Compensation” – this means that candidates earning well are not suitable. While its just the opposite case for most other job openings.
  • C++ Developer position assigns positive weightage to “Total Experience” but negative weightage to “Relevant Experience”. The requirement was for a broader skillset beyond just C++.

We can go on verifying the reasons for what turns out to be a fairly distributed set of values for weightages for various attributes. Each job opening has pretty much independent assessment of the resumes and candidates.

As expected we observed that accuracy generally increases with sample size or size of the training set.As mentioned earlier accuracy was observed to be low in the case of job openings that remained open for long and the selection criteria underwent change.