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!