The Data Analytics Blog

Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.

All Posts

Automation And Machine Learning: How Much Is Too Much?

November 12, 2017 at 1:33 PM

At Principa we’ve become quite passionate about Artificial Intelligence and Machine Learning. Recently quite a bit has been published in the press about how automated machines should be allowed to get.  Most famously perhaps there have been the warnings from the likes of South African born Elon Musk and theoretical physicist Professor Stephen Hawking.

"AI is the rare case where I think we need to be proactive in regulation... by the time we are reactive... it'll be too late." - Elon Musk

While we don’t anticipate our machine learning engine morphing into Skynet any time soon(!), there are nevertheless very important questions that we are tackling at the moment.  While I won’t cover all of these issues in this post, I do want to talk about a couple of them. 

“Explainability” – a credit example

The first issue is around “explainability”.  For those who have built scorecards before you will be aware of this notion.  For example, if I was to build a scorecard for credit applications, a popular characteristic to include would be “age of applicant”.  Most scorecards would recognise a monotonic relationship – i.e.  typically, the older you are the better risk you’re likely to be. This is an easily explainable trend if you appreciate that older people are typically more financially secure than younger people. So if we build a scorecard and the resultant model represents this trend then we would happily accept this characteristic into the scorecard.

Principa1.png

Conversely we may find very different trends (albeit predictive and possibly stable when checked against the hold-out sample).  If we are unable to explain the trends then either the characteristic will be rejected from the scorecard, or the attribute groups would need to be re-classed into “explainable” groups.

When we chat to clients about these approaches the vast majority (particularly those subject to Principa2.pngheavy degrees of compliance) agree that all trends should be explainable. There are others that refute this as an “argument from personal incredulity” and tend to trust the trends observed (subject to the trends validating against a hold-out sample).

For credit models, we tend to take the conservative (former) approach, but this approach is difficult to implement within a machine learning environment (how do you model “common sense”?). That is why we manually check our models for the unexplainable once the machine has retrained the model.  

"How do you model common sense?"

Principa3.pngEnsembling

Another approach that we have employed is that we tend to deploy our models as ensemble models (i.e. incorporated with a previous tried-and-tested model). That might mean that we take 80% of the original Generation 1 score and 20% of the Machine Learning (Generation x) score to create an ensemble score (subject to both scores being scaled on the same score/odds scheme).  In that way we can ensure confidence that our new models will add some lift, but will not create unwanted instability. Other ensembling approaches are also employed.

For the 1st time in human history we are beginning to develop tools, the workings of which no-one understands.

It’s both frightening and exciting. While we are very excited about what machine learning is bringing to the market, we are cautious and employ a level of manual assessment and belts-and-braces in each of our ML assignments.  However, as our applications get wider and we delve into more complex data where it is very difficult to fully understand each trend, then what do we do?  Our philosophy is to develop or determine an approach project-by-project, but always take a conservative fall-back position.

Using machine learning in business - download guide

Thomas Maydon
Thomas Maydon
Thomas Maydon is the Head of Credit Solutions at Principa. With over 13 years of experience in the Southern African, West African and Middle Eastern retail credit markets, Tom has primarily been involved in consulting, analytics, credit bureau and predictive modelling services. He has experience in all aspects of the credit life cycle (in multiple industries) including intelligent prospecting, originations, strategy simulation, affordability analysis, behavioural modelling, pricing analysis, collections processes, and provisions (including Basel II) and profitability calculations.

Latest Posts

The Top 6 Ways To Improve Motivation Levels In A Call Centre

Staff motivation levels are an important factor in every business, but even more so in a client or prospect facing environment such as a call centre. If your call centre agents are motivated, you can expect them to remain an employee for a longer period of time, reducing staff turnover. This not only saves you a lot of resources for recruiting, but also for training.

The Difference Between A Live Chat and A Chatbot

Most websites or apps lately have a chat function, whether that be a chatbot or a live chat function. But many people (and some businesses) don’t know the difference between the two and aren’t sure when they are talking to (or have installed) a bot or an agent.

How To Get Started With Machine Learning

The benefits have been recounted many times, but now that Machine Learning has the business world’s attention, how does one get started?  Moving into the machine learning space can be somewhat daunting, but we hope this blog post provides some guidance that you will find helpful.