AM Research is a division of Aspiring Minds. Aspiring Minds aspires to build an assessment-driven job marketplace (a SAT/GRE for jobs) to drive accountability in higher education and meritocracy in labor markets. The products developed based on our research has impacted more than two million lives and the resulting data is a source of continuous new research.

A cocktail of assessment, HR, machine learning, data science, education, social impact with two teaspoons of common sense stirred in it.

Scaling up machine learning to grade computer programs for 1000s of questions in multiple languages

Machine learning has helped solved many grading challenges – spoken english, essay grading, program grading and math problem grading to cite a few examples. However, there is a big impedance in using these methods in real world settings. This is because one needs to build an ML model for every question/prompt – for instance, in essay grading, a different model designed to grade an essay on ‘Socialism’ will be very different from one which can grade essays on ‘Theatre’. These models require a large number of expert rated samples and a fresh model building exercise each time. A real-world practical assessment works on 100s of questions which then translates to requiring 100s of graders and 100s of models. The approach doesn’t yield to be scalable, takes too much time and most of the times, is impractical.

In our KDD paper accepted today, we solve this challenge quite a bit for grading computer programs. In KDD 2014, we had presented the first machine learning approach to grade computer programs, but we had to build a model per problem. We have now invented a technique where we need no expert graded samples for a new problem and we don’t need to build any new models! As soon as we have around a few tens of ‘good’ codes for a problem (automatically identified using test case coverage and static analysis), our newly invented question-agnostic models automatically take charge. How will this help us? With this technology, our machine learning based models can scale, in an automated way, to grade 1000s of questions in multiple languages in a really short span of time. Within a couple of weeks of a new question being introduced into our question pool, the machine learning evaluation kicks in.

There were couple of innovations which led to this work, a semi-supervised approach to model building:

  • We can identify a subset of the ‘good’ set automatically. In the case of programs, the ‘good set’, codes which get a high grade, can be identified automatically using test cases. We exploit this to find other programs similar to these in a feature space that we define. To get a sense of this, think of a distance measure from programs identified as part of the ‘good set’. Such a ‘nearness’ feature would then correlate with grades across questions irrespective of whether it is a binary search problem or a tree traversal problem. Such features help us build generic models across questions.

  • We design a number of such features which are invariant to the question and correlate to the expert grade. These features are inspired by the grammar we proposed in our earlier work. For instance, one feature is how different is an unseen program from the set of keywords present in the ‘good set’; while another is the difference in the programs in the kind of computations they are doing. Using such features, we learn generic models for a set of problems using supervised learning. These generic models work super well for any new problem as soon as we get our set of good codes!

Check out this illustrative and easy-to-grasp video which demonstrates our latest innovation.


The table presents a snapshot of the results presented in the paper. As shown in the last two columns, the ‘question-independent’ machine learning model (ML Model) constantly outperforms the test suite based baseline (Baseline). The claim of ‘question-independence’ is corroborated by similar and encouraging results (depicted in last three rows) obtained on totally unseen questions, which were not used to train the model.

Question Set
ML Model
All questions
All questions
All questions
Unseen questions only
Unseen questions only
Unseen questions only

What does this all mean?

  • We can really scale ML based grading of computer programs. We can continue to add new problems and the models will automatically start working within a couple of weeks.
  • These set of innovations apply to a number of other problems where we can automatically identify a good set. For instance, in circuit solving problems, the ones with the correct final answer could be considered a good set; this can similarly be applied to mathematics problems or an automata design problem; problems where computer science techniques are mature to verify functional correctness of a solution. Machine learning can automatically then help grade other unseen responses using this information.

Hoping to see more and more ML applied to grading!


Work done with Gursimran Singh and Shashank Srikant

An Automated Test of Motor Skills for Job Prediction and Feedback

We’re pleased to announce that our recent work on designing automated assessments to test motor skills (skills like finger dexterity and wrist dexterity) has been accepted for publication at the 9th International Conference on Educational Data Mining (EDM 2016).
Here are some highlights of our work –

  • The need: Motor skills are required in a large number of blue collar jobs today. However, no automated means exist to test and provide feedback on these skills. We explore the use of touch-screen surfaces and tablet-apps to measure these skills.
  • Gamified apps: We design novel app-based gamified tests to measure one’s motor skills. We’ve designed apps to specifically check finger dexterity, manual dexterity and multilimb co-ordination.









  • Validation on three jobs: We validated the scores from the apps on three different job roles – tailoring, plumbing and carpentry. The results we present make a strong case for using such automated, touch-screen based tests in job selection and to provide automatic feedback for test-takers to improve their skills!

If you’re interested in the work and would like to learn more, please feel free to write to

Data Science For Kids Goes International

We successfully organised our first international data science workshop for kids at the University of Illinois as a part of SAIL, a one-day event to learn more about life on campus by attending classes taught by current students.
The workshop aimed towards introducing the idea of machine learning and data-driven techniques to middle-to-high-school kids. Participants went through a fun exercise to understand the complete data science pipeline starting from problem formulation to prediction and analysis.cssail
Special mention and thanks to the mentors, Narender Gupta, Colin Graber and Raghav Batta, students at the university who helped us execute the academic and peripheral logistics of the workshop efficiently and making the experience engaging and interesting for the attendees.









Narender Gupta                     Colin Graber                          Raghav Batta

To read the mentor experiences click here.
Visit for more information on the event or workshop.

What AM Research told you in 2015 – the data science way?

As the year came to an end, we looked back on what we shared with the world in 2015. As data nerds, we pushed all our blog articles in to an NLP engine to cluster them to identify key themes. Given the small sample size and challenges to find semantic similarity in our specialized area, we waded through millions of unsupervised samples through deep learning with a Bayesian framework, ran it on a cluster of GPUs for a month…yada yada. Well, for some problems it is just that humans can do things easily and efficiently; so that is what we actually did.

The key themes were:

Grading of programs – 4 posts

We need to grade programs better to be able to give automated feedback to learners and help companies hire more efficiently and expand the pool considered for hiring. We at AM dream to have an automated teaching assistant – we think it is possible and will be disruptive. Thus we dedicated 4 of our posts on telling you about automatically grading programs and its impact.

The tree of program difficulty – We found that we could determine the empirical difficulty of a programming problem based on the data structures it uses, the control structures used and its return type, among other parameters. We used these features in a nice decision tree to predict how many test takers would answer the question correctly, and we predicted with a correlation of 0.81! This tells us about human cognition, helps improve pedagogy and also helps generate the right questions to have a balanced test. And this is just the tip of the iceberg. Second, we approached the same by looking at the difficulty of test-cases and their inter correlation. We understood what conceptual mistakes people make and also got a recipe to make better test cases for programs and had insights on how to score them. For instance, we found that a trailing comma in a test case can make it unnecessarily difficult!

Finding super good programmers – Given these thoughts on how to construct a programming test and score it, we showed you how all this intelligence put together with our super semantic machine learning algorithm, we can spot 16% good programmers missed by test case based measures. Additionally, we also found automatically the super good ones writing efficient and maintainable code. So please say a BIG NO to test case based programming assessment tools!


Reproduced from “AI can help you spot the right programmers”. It shows a test case metric misses 16% good programmers. Furthermore AI can help spot 20% super good coders

Pre-reqs to learn programming - Stepping back, we tried determining who could learn programming through a short duration course. We found that it was a function of a person’s logical ability and English but not did not depend on her/his quantitative skills. Interestingly, we found that a basic exposure to programming language could compensate for lower logical ability in predicting a successful student who could learn programming. A data way to find course prerequisites!

Building a machine learning ecosystem – 3 posts

Catching them young! We designed a cognitively manageable hands-on supervised learning exercise for 5th-9th graders. We helped kids, in three workshops spread across different cities, make fairly accurate friend predictors with great success! We think data science is going to become a horizontal skill across job roles and want to find ways to get it into schools, universities and informal education.

“Exams. I would take my exam results, from the report card of every year. And then I will make it on excel and then I will remember the grades and the one I get more grades I will take a gift” [sic.]


Reproduced from Whom will you befriend? Can machine learning models devised by high school kids predict this?

The ML India ecosystem – Our next victims were those in universities. We launched to catalyse the Indian machine learning ecosystem. Given India’s very low research output in machine learning, we have put together a resource center and a mail list to promote machine learning. We also declared ourselves as self-styled evaluators of machine learning research in India and promise to share monthly updates.

Employment outcome data release – We recently launched AMEO, our employability outcome data set at CODS. This unique data set has assessment details, education and demographic details of close to 6000 students together with their employment outcomes – first job designation and salary. This can tell us so much about the labor market to guide students and also identify gaps – to guide policy makers. We are keenly looking forward to what wonderful insights we get from the crowd! Come, contribute!

Pat our back! – 3 posts 


Reproduced from “Work on spoken English grading gets accepted at ACL, AM-R&D going to Beijing!”. We describe our system that mixes machine learning with crowdsourcing to do spontaneous speech evaluation

We told you about our KDD and ACL papers on automatic spoken English evaluation – the first semi-automated automated grading of free speech. We loved mixing crowdsourcing with machine learning – a cross between peer and machine grading – to do super reliable automated evaluation.

And then our ICML workshop paper talked about how to build models of ‘employability’ – interpretable, theoretically plausible yet non-linear models which could predict outcome based on grades. More than 200 organizations have benefited by using this model in recruiting talent and they do way better than linear models!

Other posts

On the posts off these three clusters, we told you about –
Why we exist – why we need data science to promote labor market meritoracy

– The state of the art and goals for assessment research for the next decade (See ASSESS 2015)

Our work on classifying with 80-80 accuracy for 1500+ classes

It has been an interesting year at AM, learning from all our peers and contributing our bit to research, while using it to build super products. We promise to treat you with a lot more interesting stuff in open-response grading, labor market standardizing and understanding next year. Stay tuned to this space!


Aspiring Minds releases AMCAT employment data at CODS 2016!

Aspiring Minds Research is pleased to announce that it will be co-organizing this year’s data challenge at CODS 2016, the annual top-tier conference on machine learning and data science organized by the Indian chapter of KDD.


Undergraduates – performance and salaries
This year, we wanted data science enthusiasts to get a flavor of the kind of data we have and work on. We have released AMEO 2015 – a dataset on Aspiring Minds’ Employability Outcomes. which captures the academic and demographic information of engineering undergraduates giving AMCAT, Aspiring Minds’ battery of standardized assessments. What makes this dataset unique and rich is that it also has employment outcomes (annual salaries of students’ first jobs) along with standardized test scores.

Interesting questions
The answers to a lot of interesting questions possible lie in this dataset –

  • Can we predict the salaries a particular undergraduate would get on graduating?
  • Is the recruitment industry meritocratic – Do people with higher skills get paid higher? Or are there biases which don’t allow for these?
  • How important are English skills in getting a job?

and many more!

Participate and spread the word – 1000 USD cash prizes!
Interested in finding out the answers to these questions?
Take a stab at the data right away by downloading it from the contest website (mentioned below).

Get started right away and help spread the word and!
1000 USD cash prizes to those with the best submissions!

Contest website


Aspiring Minds is proud to be at the '9th Human Resource Study Day' in Shanghai | 25th May'18. Our Co-founder & CTO……

"‘India needs private initiative in creating great research universities like MIT and Stanford" @varaggarwal, our C……

Aspiring Minds' success story covered in Doordarshan's popular TV show, "Aap ki Baat".……

Our co-founder and CEO @himanshu0820 speaks on #AI powered #recruitment and future of #hiring at…

Our Co-founder & CEO, Himanshu Aggarwal will be speaking today @asugsvsummit. Definitely not to be missed!……

Aspiring Minds is proud to be a #ASUGSV2018 'Participating Company'. Our Co-founder & CEO, @himanshu0820, will be……

"Humans need to learn to work with machines as machines have learnt to work with humans" ~@varaggarwal, Co-founder……

Humans need to learn to work with machines as machines have learnt from humans : @varaggarwal talks on Transforming……

Wipro's top-gear learning environment facilitates #upskilling for @Wipro employees ~ @SunilKalachar, Global Head, W……

#Technology is an enabler in redefining the #candidateexperience and reducing the supply demand gap in…

"Evaluating #Programming ability in freshers is now a must" ~ @SunilKalachar, Global Head, Wipro Campus Hiring Team @Wipro #DIGIHRSUMMIT

"Companies changing #hiring strategy is a result of evolving #IT landscape. Necessity of #automation in #HR process……

"Paradigm shift in expectation from millennials - To be on a constant learning curve. Evolve as per constantly evol……

#Skills are becoming obsolete and it's important to embrace new age skills ~@sdwivedy…

A glimpse of spellbound audience all ears to hear what lies ahead in #HRTech #skills are evolving constantly and……

And we begin...#automation powered by AI and #robotstransforminh #HR in the IT/ITeS industry | The Future of……

The stage is set! Welcome to Aspiring Minds #future of #digital #HR summit #futureofwork #DIGIHRSUMMIT

Twitter Media

The future of Digital HR is here: Stage all set for our Bangalore Summit #futureofwork #HR #Hiring #IT…

Here's our impressive panel of speakers for #DIGIHRSUMMIT. We are up for some very interesting conversations tomorr……

Hear Preeti Das, Executive Vice President, Sutherland Global Services will be speaking on AI led HR transformations……

As digital transformation sets in, how will companies remodel their business strategies and redefine the future of……

Aspiring Minds’ English language assessments r powered by #MachineLearning & #speech recognition technology to scie……

With #AI and #automation rewriting traditional #recruitment mechanics, what is in store for #HR in 2018? Join us fo……

Launched today!! Our Co-Founder & CTO, @varaggarwal's latest book "IndiaNext". It shares compelling facts about Ind……

#CustomerService and #Accounting jobs have the highest #AUTOMATION potential in 2018. General management &……

Inductive and deductive #reasoning will emerge as the most sought-after #skills in 2018! Aspiring Minds report on F……

In this era of #AUTOMATION powered by #ArtificialIntelligence and #bots, which #Jobs will survive in 2018? Read Asp……

Aspiring Minds revelation of "80% #Engineering students found unemployable" continues to raise doubts on quality of……

Right #aptitude and right #attitude are two critical parameters for success. While #machines can have the former, t……

Top industry stalwarts | 1 stage | Great Conversations|Launch of Aspiring Minds Autoview -…

#Autoview is The Future of #Digital #HR. Measures for multiple #skills across myriad #job roles. Generates suitabi……

Launching the latest invention from AM Research Labs #Autoview - #ArtificialIntelligence Intelligence and……

It's difficult to find the right people to #interview candidates ~ Johnson Varkey, VP Industry Vertical, Aspiring M……

Time for Q&A session between audience and experts ~ Will leadership competency grow narrow globally over a period o……

Ability to handle #data require substantial effort. @Joydeeproy on #ArtificialIntelligence led transformation in……

"Industry is now scouting for #talent that's high in quality and is experienced. #innovation in workforce is key"……

What was relevant yesterday is not relevant today and what is relevant today will not be relevant tomorrow ~ Pralay……

#MachineLearning algorithms and AI as means of #skill #evaluation leads to better matching between workers and jobs! #DIGIHRSUMMIT

A glimpse of spellbound audience all ears to hear what lies ahead in #HRTech #skills are evolving constantly and……

#automation and its impact on #Jobs. Which #skills will get redundant and what is going to rule? Manuj Sethi on the……

#technology driven #disruption in #HR is no longer a premise in the offing. Manuj Sethi, VP, Client Engagement……

Manuj Sethi, VP Aspiring Minds talks on AM's contribution is evaluating job competencies and helping in #Hiring the……

Registrations galore at Aspiring Minds product launch event. Ambience is abuzz with great talks and networking! Sta……

The stage is set! Welcome to Aspiring Minds product launch event. The Future of #Digital #HR - Top #tech for Top Ta……

Hear @Joydeeproy , FS Advisory Partner at @PwC_IN speak on The #Future of #Business and #Technology led transforma……

Hear Pralay Mondal, Senior Group President at @YESBANK speak on The #future of #Businesses and #technology led tran……

We are back! We thank everyone for your extended support and eagerly look forward to meeting you. 13 December 2017……

With deep regret, we inform you that due to #MumbaiRains & cyclone warning issued by Govt, we have postponed the As……

The stage is set! We eagerly look forward to meeting you today at the @AspiringMindsAM product launch event.……

Start early! #placement preparation should start from 1st year of college and not in the #final year!…