10 Machine Learning use cases for HR

Hi there,

These days we seem to be bombarded daily with articles about Artificial Intelligence, Machine Learning and some version of ‘robots will take your job’… However as of 2016, machine learning is a buzzword, and according to the Gartner hype cycle of 2016, at its peak of inflated expectations.[12] This is because finding patterns is hard, often we don’t have enough training data available, and also because of the high expectations it often fails to deliver – so hold your expectations of having a ‘Jarvis‘-like presence guiding you along – we’re not quite there yet 🙂


With that in mind, I thought it would be interesting as an HR/IT professional to try to identify possible use cases in HR for machine learning, and then identify where the most value can be gained from using it. And by HR /Human Resources here I mean all the ‘branches’ of it – including Recruitment, Personnel Administration, Talent & Performance Management, Payroll, Time management, Benefits, Compensation etc etc. I’d be happy to have comments & additions be added to the list, so leave your suggestion/s in the comments section below. With that said, here we go:

Use cases for Machine Learning

1/ Recruitment, candidate attraction – explore your social media data / mentions, and dig down where traffic – with a focus on target market (say front-end engineers) are coming from, in order to achieve more predictable candidate flow. And remember positive impression matter a lot, as Chobani has shown with HR as PR. Then use blog post writing software for example using Narrative Language Generation, in order to improve social media presence.

2/ Recruitment to Talent Management –  explore your data to classify from which industries / areas successful candidates have come. Can you find commonalities between solid performers? You can use for example K-means clustering to find the commonalities between the good performers. However as this article explains, this can lead to bias in your selection (say as most CS graduates are male), so it’s important to back test your algorithm to avoid issues down the road.

3/ Recruitment, candidate selection – use natural language understanding or algorithmic selection tools on candidate resume pools to find suitable candidates.

4/ HR customer service – as explored here, with Natural Language Understanding getting better and better it’s possible to create chatbots (or conversational agents) that help answer employee questions, route questions to human agents, perhaps even do simple updates. Companies in this space include eg. Talla, Kylie,ai. Custom implementations could be done with Slack, Microsoft’s botframework, or IBM Watson conversations etc. I’m working on a ‘Benefits’ chatbot using Watson Conversations and SAP Hana Cloud Platform, welcome to ping me here if you are interested in this space.

5/ New hire on-boarding – chatbots these days use NLP (Natural Language Processing) which ‘understands’ what the employee is intending to communicate. You could create a chatbot or ‘conversational agent’ with new hire guidance, FAQs, role documentation.

6/ Retaining valuable employees – Use salary data, performance, organizational data etc to explore correlations, and ultimately predict which factors predispose to voluntary terminations. You could do these predictions eg. with Ensemble methods / Random Forests, or use classification tools like support vector machines or a K-neighbors classifier to group the employees into ‘buckets’ of ‘high / medium / low’ chance of leaving.

7/ Performance management guidance – provide a chatbot to answer employee queries re: the performance process like this one by SAP/Successfactors.

8/Payroll & Time Management employee questions – provide a chatbot to answer employee queries re: payslips, overtime, absence policies etc, as explored here. The bot also handle repetitive tasks which can be demoralising and unfulfilling (e.g. pre-qualification (what’s this issue about?) or authorisation (how can you prove you are John Smith).

9/ Payroll data connection to talent management – highly structured data found in conventional databases tend to support traditional, highly analytical machine learning approaches. If you have 10+ years of transactional data, then you could use machine learning to find correlations between employee characteristics and pay raises for example.

10/ Career / role recommender system – If you have a large enough organisation with different departments, very varied roles and the data to track where people have previously transferred to or changed roles into, then you could also create a recommender system based on interests, skills, performance, where suitable new roles in your organization could be found. Here’s a comprehensive list of different recommender system – eg. with tools from Amazon, Microsoft Azure or IBM Watson.

Hope this whet your appetite a bit to explore Machine Learning for HR a bit further – and let me any comments or additions below!

Launch festival April 2017

Hi ya,

A few months ago I got a founder ticket to the Launch Festival in San Francisco for April 7th and 8th. After three whirlwind days in the Bay Area here are the things that stuck out to me. Personally for me / Move Correctly my best meeting was actually with Greg, the CEO of Fit3d – since he provided so much actionable, real advice. It’s just fantastic to exchange ideas with some-one in the same industry. Now here are my notes about Launch:


Machine Learning

1. The flywheel for Machine Learning – was articulated by Rob May, the CEO of Talla, is the way ML becomes better the more data there is, makes better algorithms, makes a better product, drives more use and more data … So it’s really about who can build the best/ quickest flywheel for your use case / industry, and in that sense (at least the ML companies want to give that impression) this is the time to make major investments in this area, as the first (successful) movers will have a big advantage.

2. Zorroa – are doing really impressive visual recognition from videos – where they can search inside videos / images just as if you were googling documents. So eg locating any scenes where ‘the Rock’ appears, then narrowing it down if it happens in a bank, and further where there is a Lambo in the scene.. Currently you need to plug into their REST API,  but they mentioned a SAAS app in a few months…

3. Corto – their demo of a chatbot analytics interface to a pharmaceutical genomics data was impressive, with hypergraphs / nodes flowing and a lot of complex words in the presentation, so I have no doubt the tech is solid. Their team is chock-full of smart guys, with eg one of the leading AGI guys – Ben Goertzel as Chief Scientist. What wasn’t clear for me is who will sell their product and what is their value prop?

4. The PAC framework by Rob May again, which essentially states that any company should evaluate how they want to use Machine Learning in these categories:

A) P for Predict, eg. in recruitment which candidates will perform best, in sales which products etc.

B) A for Automate, could be easing workflow, say for example NLP (natural language processing) transcribing recruitment interview notes.

C) C for Classify – say classifying best resumes into different buckets quickly

Now apply these questions across your customers, across Product, across Operations, and you should start to identify good opportunities where to apply ML.

5. Talla is a customer service bot either for IT or HR, that’s been trained to answer IT / HR questions, with a UI either in Slack or Microsoft teams. Their target market is in mid-size companies.

6. Kylie.ai –  created a customer service bot, integrated with eg ticketing systems like Zendesk. They’d ‘clone’ employee personalities and create a response integrated into existing UI’s eg on Zendesk, Salesforce, SAP etc, which the human customer service agent can review, modify, approve / send.


The Cannabis market is yuuge apparently as it warranted it’s own vertical, next to healthcare, drones, ML etc. Interesting companies included:

  1. Leaf – built a small growing unit looking like fridge, which automates home growing. Sold about 1M of them in advance and are taking orders for 2018..
  2. Alula Hydro, who have created a hydroponic, nutrient delivery system for industrial growers. The 20K industrial growing management system apparently can raise yields from a crappy 1K per pound to 5K-6K per pound.
  3. Baker, who are making a CRM / loyalty / online store SAAS for dispensaries.


Miscellaneous notes

  1.  How to get 1000 applicants for a job ad – by Tucker Max from Book in a box: 
    • Start with the hook – explain the why / the mission of the company, and if some-one doesn’t believe in that clearly they’re not a fit.
    • Sell the role – Talk like you would talk to a friend about the job. Ditch all the standard corporate lingo about ‘mission critical, pro-active go-getter with a nose for global synergies’. 
    • Pleasure and Pain – explain why the company / role is awesome, but clearly also the downsides of the job, no point in trying to sugar-coat stuff.
    • Testimonials / social proof – we use these in any ads (for soda, cars, books etc), why not for job ads?
    • Finally – the actual ‘boring’ details
  2. VR / AR – was actually a bit underwhelming – nothing really that stood out. Yes, it’s cool to get a new, different type of camera or get analytics off VR, but…eh.
  3. In hardware – Megabots was really cool, just in terms of lighting up any 6-year old inside all of us – Robots with fun big weapons (WEABOONS!) and picking up cars 😉


5 reasons solar power is coming…

In my view there are several factors, which are adding up in favor of solar electricity. These are now combining to make solar an exponential technology – eg Ray Kurzweil has predicted with current trends, the share of solar doubles every two years, meaning that solar should have a 100% share of the market in 12 years – “it has begun to reliably double its market share every two years — today’s 2% share is up from just 0.5% in 2012.”.  


The trend is driven by the following factors:

  1. The cost of solar per Watt DC going down according to the National Renewable Energy Laboratory:
  2. In over 20 US states solar is at grid parity with retail electricity according to Greentech Media.  So why is grid parity important? By grid parity we mean “Residential solar reaches grid parity when the levelized cost of solar energy falls below gross electricity bill savings in the first year of a solar PV system’s life.”  Meaning that you can buy the solar system (even 100% financed, zero down), and you will pay less in the first year, than you would have paid for electricity to your utility company. As the cost of retail electricity will likely continue to rise, and the cost of a solar installation will go lower, GTM estimate 42 states reaching grid parity by 2020.
  3. US Solar PV (photovoltaic) market growth is strong, especially the utility sector is showing a nice hockeystick (probably due to the lower costs).
  4. The fact of the matter is that not many people have an extra 15K-20K laying around, however if you do – you get the best IRR (Internal Rate of Return), around 10% depending on your state, but as high as 30% in MA, and 20% in NY, NJ. These days it’s possible to purchase a solar PV installation using financing, essentially paying for the solar installation using the savings in your electricity bill. I.e. no money down, and after 10 years the system is yours, and the electricity produced from it is ‘free’. The options for lease / purchase for example by sunrun.com shown here;
  5. And the final factor – according to research by Lawrence Berkeley National Laboratory found that home buyers were likely to pay on average $15.000 dollars more for a home with a solar system installed (even small 3.6 KW system), compared to a home without one. So not only would you be able to reduce or eliminate your electricity bill, but you would essentially get the money back on your investment when / if you sell your home.

So, you know this thing about climate change? That it’s not a hoax, even the permafrost in Siberia is thawing etc, right? Given the above info, I know I would install solar power in my house (if having a house was on the radar..), how about you?

Thanks for reading.