“We want to predict -X-.” Fill in any desirable topic on the location of the X and you have the formulation of a use-case in the way many companies today think about analytics use-cases. In order of increasing probability of success of such use-cases: X equals the winning lottery number, the future price of crude oil, windows falling from high-rise buildings (not kidding; actual use-case) and finally, a customer buying a mortgage.
This post deals with understanding the importance of the use-case identification. The word ‘identification’ here hints at the effort involved. Identifying a use-case resembles doing a reconstruction of your house: rather than dreaming up a random extension to your house, you will consider in great care its purpose, its sizing and its connection to the existing structure. Subsequently, this gives input to the construction plan and the bill of material.
Let’s start with an example where the use-case is taken too lightly.
An Australian bank wants to predict which customers are likely to buy a mortgage.
This sounds like a valid use-case, right? Upon discussion with the bank, the use-case already seemed decided on: predict the mortgage take-up, take it or leave it. Moreover, following the recent hype on deep learning, the bank had set their eyes on neural networks of some kind. ‘Traditional’ machine learning would not do: another take it or leave it. Data sources were provided as indicated in Figure 1. The question on how the model was intended to be used, was not relevant: that was a case for marketing. After all, with a success criterion of model accuracy set to 80%, a model is a model and leads to predictions; marketing knows how to deal with lead lists.
So, use-case done. Time to bring in the guy with the sexiest job of the 21th century. In a previous conversation, he had uttered something about ‘Dueling deep double Q-learning’ and ‘Dilated pooling layer highway networks’, so the bank was highly convinced of his magic.
At first sight, the modeling data (Figure 2) looked rich. Although the CRM data lacked deeper insights in the customer, such as family composition or description of life phases, the available data was clean and complete.
The bank had gone through a merger: a retail bank and a private investment bank had merged and the customers of both parties had not yet been mapped and hence, from retail perspective, any investment account, including investment behavior was invisible for modeling. For usage data, there were the high-level indices such in-and outgoing flow and the change thereof. A recent project had developed event based marketing signals, and as such, detections of large deposits and alike were also available. Finally, to better understand customer behavior, the bank had gone through an effort to classify transactions into high-level categories such as food and utilities.
The model and its true face
The model was built and the company was delighted to learn that the model accuracy was 94.7%. Hail the data scientist! The lead list was generated, and sent to the call center. After a few days of calling, disappointment started kicking in: maybe they had sent in the wrong list, because none of the customers was even considering a mortgage at the time.
A port-mortem was conducted. The list was found to be correct. Moreover, the data scientist has identified a cut-off point for the propensities, finding a lift of 4 for the top 5% of customers, a number not uncommon for many marketing models.
To deeper understand the model performance, let’s see the bigger picture here. The bank has a million customers and sells 5,000 mortgages per year. This results in a 0.5% take rate. If a model has a lift of 4 @5%, it means that for the 5% customers with the highest propensities, the take-rate is 2%. In other words: the model is 98% wrong for that subset. This is exactly what they experienced in the call center.
Inspecting the 5% target group showed that the model identified all customers who were indeed feasible to take a mortgage: those customers in their mid-twenties, with enough financial means and social/economical background to settle. Yet, this was not at all what the bank was interested in: they were looking to identify customers who are on the verge of buying a mortgage, so they can do a timely offer.
Another important aspect was uncovered: the model was not very dynamic. Scoring this model monthly would yield the same customers repeatedly. Indeed, how often do you get in and out the age range of 23-28, or how often do your savings significantly change?
What fails? Analytics or use-case?
It’s well-know that model accuracy is a misleading measure, and while the data scientist looked at the correct model performance measures (AUC: 0.57, F1: 0.04), the bank only focused on the accuracy as success measure, which they had set at 80% (and indeed, without properly understanding the implication of the numerical recipe of accuracy) and they considered the 94.7% model accuracy as a go signal.
The real issue is two-fold: firstly, it was never up for debate how the predictions were going to be used and secondly, it was never considered if the available data could give rise to predictions of a required accuracy.
The data question
The two points above go hand in hand, but starting with the data: a model only gets as accurate as the structure in the data dictates, whether you use ‘simple’ models or deep learning model. In the latter case, you even run the risk of being blinded by technicalities rather than the business implications of the prediction. Or maybe to phrase it funkier:
Models are not magic, nor does the data hide endless secrets. There’s a few questions one can ask to find out if modeling could result in a model with a desired level of accuracy:
- What are conceivable relations between the predictor data and the target?
- How many customers have the same values of the predictor data and are the values dynamic?
- If you have an expert manually inspect one customer data records, can they indicate which customer are likely to buy soon?
Answering those questions for the mortgage case:
- Indeed, the model captured mortgage feasibility. If you have enough income or savings, then you may buy a house, or negated: if your income is too low, you can’t buy a house (ok, don’t think NINO – subprime lending). Also, being in a certain age range makes you more likely to buy a house. However, those indicators won’t provide a high-quality signal. This is where you see the usual (model) lifts of 3-6.
- Many customers have similar combination of age range and income (and even banking products and spending habits). Yet, they are not all buying a house and hence, a model is limited to modeling (or ‘finding’) the average effect of the group. Also, as mentioned in the previous section, the dynamic nature of the data will indicate how quickly the likelihood to buy a mortgage increases or decreases. If the most important predictors are age and income, then month after month, the model will yield the same list of customers, and by the simple fact that customers buy a mortgage every 10 years, the model is bound to have low accuracy.
- An expert who manually investigated the data, identified feasibility, however, by no means any strong signals. This once more is an indication that the resulting model will not be highly accurate.
The expert had more to say: if people get married, they don’t have a mortgage yet and they are in the feasible category, then they are much more likely to be looking for a house. Same holds for customers living in a small house that just had their first born. Another pearl of wisdom: if people do not extend their yearly cable contracts, it might indicate they are planning to move. Or what about customers subscribing to a realtor magazine?
It’s well worth listening to those stories and subsequently roaming over the thought how to observe those things in data. People getting married? Your financial transactions indicate a huge marriage signature, given the costs and the enormous amount of arrangements one must make. Think of the single transaction in the jewelry store that even signals the upcoming proposal -your bank knows it earlier than your fiancée. Similar mechanisms can be considered for children on the way, or even subscriptions of magazines. Within the limits of the laws of privacy, those signals can provide an invaluable understanding a customer life and hence, the proper alignment with financial products.
Don’t throw the low-accuracy model; learn how to use them.
The previous paragraph answer the data question; this paragraph focuses on understanding how to use the model, given its accuracy.
The simplest rule is: understand how well you do today, and if a model does better, use the model, keep the action mechanism constant. For example, if today your campaign responses are 1%, a (silly) predictive model that achieves a 2% campaign response, doubles the effectiveness of your campaigns. However, few people would cheer over a model that is 98% of the time wrong.
Digging deeper into this: like treating customers according to their value, one should treat models per accuracy. You don’t get rid of low value customers, you just align your efforts with their value (another useful analytics project!). As for models: low accuracy models are used for improving upon business rules. One can even consider coding the business rules into predictors and incorporate them in a predictive model. Understand this as calibrating the business rules against historic data. Next, use the models to collect more data:
For the mortgage case, rather than calling up customers based on the lead list, one could send them an email newsletter with a link to a lending calculator. Subsequently, ensure that that you capture customers following the link and use that data (after analytically processing it) as next stage for the lead development process.
Maybe a healthy way of qualifying what analytics can achieve is:
An Australian bank wants to develop an analytics driven mortgage lead management process.
How is this for a use-case? Not your best elevator pitch, but far more realistic and aligned than the previous use-case. ‘Analytics driven’ seem to indicate there are multiple analytics components; not the single 99% accurate model. The words ‘develop’ and ‘lead management’ indicate an involved business on a journey now joined by data scientists that can add an empirical perspective. The wording of the use-case opens for a wide range of analytical initiatives:
Analytical derivation of current renter vs. owner
Based on transactional level data one can detect if a customer pays a mortgage or rent. This information will guide the items for a newsletter (“how to use your property as an investment” vs. “10 things to consider for buying your first home”)
Mortgage feasibility estimation
This is the ‘failing’ model discussed in this post. Based on income, expense and savings one can carve out a large group of customers that never need to be bothered with mortgage proposals (read: bother them with more relevant proposals)
Looking for specific signals in transactional level data. (e.g. marriage, children, divorce, job change, etc.)
Mortgage purpose prediction
Based on the above segmentation and additional transactional level data, it should be a good practice for a bank to consider ‘Is buying a house good for this customer?’ Purpose meaning: mimic the advice of a financial advisor on this matter and apply it in scale.
Interest estimation based on click-through rate on newsletter items
One click isn’t equal to interest. Analytics can help purify signals. For example: in the “How much can I borrow?” example, relate the filled-out information to the known/derived income or understand how filling out such items are positioned in the time-path of buying a house.
Next Best Action for newsletter topics
Based on feasibility, customer segment and click-through rates, predict which topics are of interest to customers to make up personalized newsletter.
Lead list generation for call center
When finally, in the prospect phase, based on identified signals, a predictive model may be strong enough to justify making personal calls and have a mortgage conversion with a customer.
Clearly, the list of initiatives is far from complete. Consider there’s no such thing as a complete list or an out of the box process. At the end of the day, every bank (or more generic, industry) has their own processes, their own customer dynamics and their own data. However, the list of initiatives does show that analytics is not a one-shot model approach, but a welcome, empirical based, accompaniment of existing business processes. To develop this, consider giving the business an active role, ensure they get educated enough to look at predictive models from a business evaluation perspective and ensure the development of an (in-house) data science team that can help identifying the right use-cases. After all, who doesn’t want to work with people with the sexiest job of the 21th century?