Deploying predictive models, and why the modelling algorithm is perhaps the easiest aspect of the problem.

Predictive models, specifically propensity models, are a staple of data science practice across organizations and verticals. Be it to understand whether a customer is likely to respond to an offer, or whether a borrower is likely to default, we find them applied in a variety of situations. In specific verticals such as financial services, their use is so prevalent that one finds entire divisions devoted to the care, feeding and updating of these models. 

However, as is the case with so many things where we confuse volume for variety, the majority of these problems, as well as what we need to do to solve them, are standard. This implies that it is very much possible to productize model scores. Here are some of the common features of these models, and what they imply for someone trying to productize, or at least streamline, model building.

Problem statements

Most models end up falling into one of the following categories:

1. The propensity of a customer to transact in the next n days, either in general or in a specific product category
2. The propensity of a customer to respond to a specific offer (as a function of both offer and customer features)
3. The propensity of a customer to churn, either implicitly (i.e., through inactivity for a certain period) or explicitly (i.e., account closure)

It is therefore possible to provide, with minimal configuration options, a set of standard models out of the box. These standard models will cover the majority of use cases.

Typical configuration options that make sense are:

1. What is the response horizon?
2. What is the nature of response being predicted? Transaction, Cart addition, Closure etc.
3. What are the products being tracked? All products, products in a specific category etc.
4. Is the model restricted to:
   1. Active customers
   2. Customers who have purchased this product before
   3. Customers who have never purchased this product before
   4. Unrestricted – applies to all customers

Feature engineering

The features used in most of these models are similar, and involve a standard set of patterns of extraction and preprocessing. Depending on the model, some specialized features might be called for, but these are, by and large, small modifications to a general feature set.

It is possible to standardize feature engineering for the most part. The ones that typically matter are: 

1. RFM and related features 
2. Preferences on product attributes, price, time, location channel, etc
3. Response to past marketing outreaches
4. Socio-demographics if available
5. Service history, if any
6. Preferences for the relevant product subset, if applicable (for instance, if the model predicts the propensity to buy Menswear, has the customer already exhibited a preference for this category?)

Additionally, for businesses where the value of the product is relevant to transactions (share price, NAV of a mutual fund etc), features pertaining to these aspects might be useful.

Model building pipeline

Model relevance depends on regular retraining and scoring, especially in businesses where the pattern of customer behaviour might be very dynamic.

ML Ops matters. One can set up a standard pipeline that is scheduled to run regularly, and retrain and rescore models with updated data on a regular basis. Since features and models are standardized, this does not require ongoing manual effort once it is set up. One can also create a mechanism to track performance on standard metrics such as recall at various deciles, area under the ROC curve etc.

A typical pipeline to train a model can be as follows. Consider a model to predict whether customers will transact between March 1-7, 2024. The predictors for this model would be whatever we know about each customer as of 29 February.

In order to train this model, the easiest thing to do is to go back by a week. That is, find out what you know about your customers as of 22 February, observe responses between 23-29 February, and build a model to correlate the two.

Figure 2 Training data measurement

The model built based on the above data can be used to score customers as of 29 February. In order to test whether the approach works well when applied at a later time point, one can also build an additional model based on responses between Feb 16-22, and then use that model to score data for the week following (generated as described in Figure 2 above), and then compare the scores against reality (we already know who transacted between Feb 23-29) to get a performance measurement.

The overall pipeline now looks like this:

Figure 3 Training and scoring pipeline for model to predict transactions in the next 7 days

The exact same pipeline can be updated to work every seven days so that the model is kept up to date. The interesting thing is: it applies even when we need to customize certain aspects. For instance:

1. It is possible, in order to account for seasonal behaviour, to specify the response window dates manually, e.g., when one wishes to predict response during an end-of-season sale (EOSS), the response window to train the model would be the dates of the previous EOSS.
2. If one wishes to add customized features specific to a particular client, all that is needed is for us to add a mechanism to insert custom feature computation code in the above pipeline, while computing customer level features. The rest remains the same.

Modelling technique and Explainability

In reality, the modelling algorithm seldom matters for most problems. The performance of various modelling algorithms is usually comparable. While nonlinear machine learning algorithms do a bit better than logistic regression in a number of cases, there is little to choose between these ML models themselves. What people might look for, however, is explainability.

Model explainability is often asked for by decision makers who use them. However, explainability doesn’t always mean being able to simplify the functional form to the point where it is easy to make out what leads to the final score.

Often, what is required is simply an explanation of the various features that go into the model, along with their relative importance in the final model.

We can choose an approach where fine-tuning is minimal, the libraries are reliable and efficient, and there is support for simple things like categorical variables, missing data etc. without having to build complex preprocessing pipelines. As for explainability, it is possible to set up a standard, model-agnostic pipeline to estimate feature importance in a model. 

For instance, if you shuffle one feature while keeping the others constant, and check the performance degradation as a result, you can expect to find that the more important features cause more degradation when they are shuffled. Simply shuffle one feature at a time and order them based on how much worse the model does when you do.

Additionally, if you know already that you’re likely to pick the top 3 deciles for a campaign, simply run a decision tree to classify people in the top 3 score deciles versus the bottom 7 – this is not the same as the actual model, but can give you a simple rule that explains, at a somewhat coarse level, what is common to the customers with high propensity scores.

In conclusion…

We tend to think of propensity modelling problems as the province of data scientists. To a certain extent, this is true; however, it helps to recognize that: 

1. While there is a long tail of specialized problems that require bespoke model builds, the vast majority of problems are well understood and commoditized
2. Even for bespoke problems, the vast majority of things to do in order to build the model (feature engineering, training and validation, routine recalibration etc) are well understood and commoditized

This in turn means that decision makers can be armed with a variety of propensity scores for personalized targeting, with very little effort. This can considerably improve the effectiveness of their marketing outreach efforts.

The problem of personalizing customer engagement can be broken down into three broad problems:

1. Recording how customers engage with the brand: the most obvious aspect of this is a transaction, but non-transactional signals such as web/app behaviour, service-related communications etc. can be considered as well.
2. Parsing customer engagement records to determine how, when and what to talk to the customer about. This is where machine learning and other aspects of intelligence come into play.
3. Actually reaching out or reacting to the customer in a personalized manner. This is where marketing campaigns, web/app personalization etc matter.

The systems that focus on these three problems are broadly referred to as systems of record, systems of intelligence and systems of engagement respectively. Note that these need not always be separate products; rather, this is more of a conceptual division of responsibilities.

When one talks about systems of intelligence, perhaps the first problem that comes to everyone’s mind is: how can we recommend products to customers in a personalized manner? This is where recommender systems come in.

There are many algorithms that figure out how to recommend products to customers. Not all of them work spectacularly in every circumstance, so it is important to understand intuitively what their strengths are and when they work best. Horses for courses, if you will.

But why isn’t there one ring recommender to rule them all?

Well, the most obvious reason is the nature of the data itself. The fundamental, unsaid premise of personalized recommendation is that the brand knows the customer inside out, and can use this to recommend exactly the right product. When we think of this scenario, our instinct is to imagine vast reams of data about each customer. This premise is stress tested in many ways in real-life datasets.

What if the breakdown of your brand’s customer activity is as follows: 50% of your customers have visited only once, and 25% of those made that one visit over 2 years ago. 5% on the other hand, have probably visited 15 times in the past year alone. Your app penetration as a % of total sales is in single digits and climbing, but even there the same unevenness exists. 30% of your digital users have registered on your app, but haven’t bought anything, or even browsed much. But a bunch of them have browsed a lot, bought a lot etc.

The problem looks much worse when you have a lot of customers and/or products in the aggregate. Imagine a matrix (not the one where Keanu Reeves stops bullets, we mean the one with rows and columns) where the rows are customers and the columns are products. If you have a lot of customers and/or products, this matrix becomes very large.

A large matrix is problematic in two ways. First, there’s the computational cost of dealing with something of that size. Second, this matrix is likely to be very sparse, both because the matrix itself is large, but also because the customer activity is uneven, as in the above example. All of this makes the analytical problem tougher, because what any recommender is trying to do is figure out what to do with the empty cells in the matrix, i.e., which products to recommend because the customer is likely to buy them.

(Now, this is not an intractable problem. The computational angle is solved using packages that deal with large sparse matrices, and algorithms that can parallelize nicely, while the analytical angle is solved using methods that reduce the size of the matrix — product attribute-based approaches, neural embedding, matrix factorization etc).  

And then there’s the cold start problem. What if you have a new product, for which you have no transaction data? Or a new customer who has registered on your app but not browsed or bought anything?

Imagine trying to build a single algorithm that knows exactly what to do in all of these scenarios. Tough, isn’t it? That’s why it makes sense to think of different algorithms as being effective for different customer groups.

So what kinds of algorithms are there?

We’ll talk about those in this article. Not every single one of them, but we’ll cover the more popular approaches, and where they are best suited. Rather than talk about the algorithms by name, we will talk about the broad approaches, and refer to the various algorithms that fall into these categories.

People like you also bought…

This approach attempts to find similar customers to a given customer, and use their behaviour as a cue to determine what to recommend.

The most popular of these approaches is user-based collaborative filtering, which looks at user ratings for products, matches users with similar behaviour and uses this as a basis for recommendations. This approach works best when one is dealing with a lot of user behaviour, such as viewership data on a media streaming platform.

However, if one has a lot of other data characterizing a customer (e.g. in BFSI where it is more often collected as part of an application process, location intelligence in a CPG business where the customer is actually a retailer), or a lot of contextual data about the transaction that is valuable to understand behaviour (e.g. shopping time preferences or price/discount preferences in retail), a more generalized way of characterizing the customer becomes valuable. This means stepping back from collaborative filtering to a more generalized class of methods, namely lookalike models.

A variant of this approach is a purely geographical one, that might work in the CPG sector, namely: Stores near you are buying these products. This works when latitude and longitude data is available for all (or most) stores. This implicitly assumes that the location intelligence is reflected in the purchase behaviour of end-consumers in the locality, and therefore the ordering behaviour of nearby stores captures what one needs to know.

Lookalike models in general work best when you know a lot about the customer; however, they have also proven to be surprisingly effective when one is dealing with data sparsity – for instance, the best recommendation for a single transactor sometimes comes from those who have done that single transaction and maybe one more besides.

People who bought this item also bought…

This class of approaches involve mining co-purchase patterns in some form or shape. Item-based collaborative filtering, an algorithm pioneered by Amazon, is one of the best known examples, but simple co-purchase-based approaches like association rule mining are also quite effective.

The strength of this approach depends on how often people buy more than one thing. If the vast majority of customers are single transactors, there might be so little data to work with that this strategy might be a bit brittle.

The other challenge with this strategy is the sparsity of data. For instance, the number of people who bought a formal blue shirt and also bought dark grey slacks might be quite small, but the number of people who bought a formal shirt and also formal pants is likely to be much higher. This means that analyzing copurchase patterns at various levels of abstraction (i.e., figuring out patterns between groups of products rather than individual products) is critical to its effectiveness. This can either be done implicitly based on some statistical patterns that lead of product grouping, it is probably better done if a well-curated set of product attributes is present.

If you liked these, you’ll also like…

Rather than simply understand what customers bought, it is helpful to see if there are patterns across their purchases. For instance, someone might have a preference for the colour blue, whereas someone else might prefer ethnic wear. These patterns suggest that blue outfits might be a good choice to recommend to the former, while ethnic wear in the festive season might be a good time to get the latter to transact again. It is also possible to use these patterns to do the exact opposite: “we know you love our range of blues, but have you looked at what we have in checked patterns?”

All of these fall under the broad category of content-based filtering. These algorithms have proven to be extremely effective when there is a well-curated product master with many attributes.

However, our old adversary – data sparsity – is poised to strike yet again. What if the customer has purchased only one blue shirt? Do we assume that he loves blue? This is where approaches that exploit what we learn about a customer, while still leaving the door open to explore what we don’t, work best. For instance, an approach that assumes that all colours are equally preferred, and then bumps this customer’s preference for blue up by a little bit after this transaction, might work better. The more we see a customer, the more confident we are in our understanding of their preferences.

The good thing about this approach is that it solves for the cold start problem for products. A new product, by definition, is one that we have no transaction history for. This approach allows us to recommend it to customers whose preferences suggest that they might be interested in one with this product’s attributes.

Lots of customers are buying…

This is perhaps the simplest and most used recommender approach: what’s trending right now? We can slice this by location, time frame (including, for instance, what happened around the same time last year), customer attributes, product categories etc.

Trending depends solely on the aggregates, so not knowing much about some customers isn’t a deterrent. That being said, if we calculate what’s trending for narrow slices of the population (e.g. What are women in Kanpur shopping for in the Accessories section?), we might sometimes find that there isn’t a lot of sales data to back up the recommendations, and one might need to reinforce the approach with results from broader slices.

Here’s what you’re likely to buy…

What any recommender algorithm is trying to do is, in some form or shape, predict what a customer is likely to buy, and nudge them in that direction by putting those products front and center, rather than let the customer stumble upon it. So then there’s a way of modelling the problem in precisely those terms. Characterize each customer, characterize each product, characterize how customers interact with products, and use these to predict the probability that a customer will be interested in a particular product. This is now a standard two-class classification problem, and there are a million and three machine learning algorithms at your disposal to solve it.

This approach is especially useful when you’re solving a replenishment problem, i.e., what to recommend that a customer replenish, out of the items they have bought already. Use cases include CPG, grocery, food etc.

That’s a whole bunch of algorithms. How do we put these together?

As the previous descriptions might have indicated, each of the approaches we have spoken of involve a different common-sense principle, and each of them have their strengths and weaknesses depending on the situation. How, then, to decide which algorithm to use for your business? Or, if you want to get more fine-grained, how to decide which algorithm to use for which customer?

Here’s the good news: you don’t have to! There is a class of methods whose job is to combine what these algorithms produce and decide what to recommend. These are called hybrid recommenders or hybridizers. These methods depend broadly on the following factors:

1. How strongly and how often is a product recommended by the various algorithms
2. How much one can trust these algorithms, i.e., how well have they performed in the past
3. What we know about the customer, that indicates how to combine these outputs

The end result is a consolidated recommendation list comprising the output of any or all of the component algorithms.

But how do we know if the algorithms work?

There are two broad ways of assessing the performance of recommenders.

1. Active: This involves measuring the accuracy of recommendations shown to a customer, either proactively through SMS/Email/Push notifications, or reactively by way of personalizing their app/web experience when they browse. You’re measuring the accuracy of recommendations the customer sees and expresses an interest in, either through browsing or adding to their shopping cart or buying. A variant of this approach is one where the performance is compared against that of a control group who get no recommendations, or generic non-personalized recommendations.
2. Passive: This involves measuring the accuracy of recommendations generated for a customer, by comparing them against the observed behaviour post generation. This can also be done in back-testing mode, wherein the recommendations are generated as of an earlier date based on what is known at that point, and transactions since then are used for comparison.

The difference between the two approaches is simple: An active approach cares about whether the customer has seen the recommendations, and the power of the actual nudge is considered. The flip side is, you can only measure it when you know the customer has seen the recommendations, so it’s limited by those numbers.

The passive approach, on the other hand, doesn’t care if the customer has seen the recommendations. The underlying assumption is, customers will buy what they want anyway, with or without the nudge, so it makes sense to measure performance of the algorithms as though they are simply predicting what will happen. You get to measure performance of a lot of algorithms against a lot of customers (pretty much everyone who transacted), but you don’t know if the recommendations themselves would’ve nudged the customer in a particular direction.

It is obvious that both approaches have their merits, so it makes sense to do both.

In either case, we can use a variety of metrics to track the actual level of commonality between what is recommended and what is purchased. For instance, you could track how much of what is purchased is in the recommended list (i.e., recall), or how much of what is recommended is purchased (i.e., precision), or some variant or combination of these two. Additionally, you could account for:

• The rank of the recommendation
• The extent of the match (maybe the customer didn’t buy the exact same product, but something in the same subcategory)
• Whether what was recommended and/or purchased was very popular to begin with (if you recommended something rarely bought and it was mostly right, that’s probably more valuable than if you recommended something everyone buys and it turned out to be exactly right)

Okay, got it. Now how do we use these recommendations?

That, dear reader, is a story for another day. In our next article in this series, we’ll talk specifically about how recommendations can be used to personalize customer engagement.

We’ve jumped onto the ChatGPT bandwagon with our Prompt Generator. (I’m using ChatGPT as a placeholder for all LLMs, so please don’t flame me for not mentioning all the other options!)

What did we solve for?

This was initiated with a simple problem statement – brands struggle with generating creativity for targeted or personalized campaigns. For instance, at the MarTech Summit in Singapore this week, a panel discussion that had Zalora, Citibank and the likes, stated that one of their main challenges to operationalizing the personalization engine is content and creativity. Quite unimaginable right – to be in a world where the ML Algorithm has become the “easy part”.

Knowing the problem statement well led to a fairly focused solution definition: Help brands use ChatGPT to generate creative personalized messages.

So we built a Prompt Generator with a very focused use case – content for SMS/ WhatsApp/ Email/ Notifications.

The SOLUS Prompt Generator

It’s at https://prompt.solus.ai | Free and instant Sign Up | in Beta | Desktop only!

Let’s see how it works:

If the prompt you use in ChatGPT is something as basic as:

“Generate an SMS marketing message for SOLUS, an Apparel brand”

You get something like:

If you use our prompt generator, the prompt evolves to something much more refined and the results can be something like:

 And it gets better. The email copy comes out (using a good prompt, again) looking like this:

Does this work across categories? It does – we’ve tried it for Apparel, QSR, Hospitality and Travel, Mutual Funds, and even Securities!

What about all the fears and reservations against ChatGPT?

I feel these are largely mitigated here. Writing copy for direct marketing has been a fading craft for a while. Creativity has become less attuned to the needs of relevance and personalization, so to use an LLM to generate a baseline creative that ticks off all the requisite boxes from a craft perspective are very valuable. Brands often need dozens of creative templates with variants for targeted messages – this means a factory output, which in turn means there’s a solid case to use AI.  Once ChatGPT generates a message one can iterate and add own tonality to taste – but 80% of the job has been done by the AI.

There’s no sharing of data. There are no biases in the training set of ChatGPT polluting decisions – because the use case is not decisions, it’s playing an otherwise cumbersome craft.

What’s the catch?

You still need to know what you want. In our prompt generator, you’ll need to give inputs of the Hook, the Tonality, what Personalization to use, whether you want a Follow-up message etc. I’ve been told this is intimidating, and many folks in marketing will not have answers to these Qs. Well, there’s always the option to leave these blank – but that’s also a bit of a shame. Whoever is generating your copy – Human or AI – needs a good brief!

Let us know, please.

Use the prompt generator, or have folks in your marketing team give it a spin. And let us know if it works for you, and how we can improve it.

Click here to try our prompt generator | Free and instant Sign Up | in Beta | Desktop only!

In today’s digital landscape, direct-to-consumer (D2C) marketing has emerged as a powerful strategy for brands to establish a direct connection with their customers. The key to success in this competitive environment lies in delivering personalised experiences that resonate with individual consumers. In this article, we will explore the significance of personalisation for D2C marketing and how it can be leveraged to drive engagement, loyalty, and ultimately, business growth.

What is Personalisation For D2C Marketing

Personalisation in D2C marketing refers to tailoring marketing efforts, product recommendations, and offers to meet the unique needs and preferences of individual consumers. It goes beyond simply addressing customers by their first names or segmenting them based on general demographics. True personalisation involves leveraging data and insights to create meaningful, one-to-one interactions with consumers.

Leveraging Data for Personalisation For D2C Marketing

Data lies at the heart of personalisation for D2C marketing. Through advanced analytics and tracking tools, brands can gather valuable information about customer behaviour, preferences, and purchase history. This data can then be used to create intelligent customer insights, allowing marketers to understand their audience better and anticipate their needs.

To effectively leverage data for personalisation, brands need to invest in robust customer relationship management (CRM) systems. These systems can collect, organise, and analyse data from various touchpoints, such as websites, social media platforms, and email marketing campaigns. By gaining a comprehensive view of each customer’s journey, brands can deliver smart campaigns that have highly personalised experiences at every interaction.

Tailoring Product Recommendations and Offers

One of the most effective ways to implement personalisation for D2C marketing is by tailoring product recommendations and offers. By analysing customer data, brands can understand the preferences, purchase history, and browsing behaviour of individual customers. Armed with this knowledge, they can deliver relevant product recommendations that align with the customer’s interests and needs.

For example, a skincare brand can use a personalisation engine to suggest specific products based on a customer’s skin type, previous purchases, or even the climate of their location. By delivering personalised recommendations, brands not only prove customers with smart shopping campaigns but also increase the likelihood of conversion and repeat purchases.

Enhancing Customer Engagement and Loyalty

Personalisation in D2C marketing goes beyond transactional interactions. It creates opportunities for brands to foster meaningful connections with their customers, ultimately leading to increased engagement and loyalty.

Through personalised email marketing campaigns, brands can deliver tailored content and offers directly to their customers’ inboxes. By addressing customers by name and delivering relevant information based on their preferences, brands can build trust and strengthen the customer-brand relationship. Moreover, personalisation can be extended to social media interactions, where targeting customers through selective content and personalised messaging can be performed by brands.

Future of Personalisation For D2C Marketing

As technology continues to evolve, the future of personalisation for D2C marketing looks promising. Advancements in artificial intelligence and machine learning enable brands to gather and analyse vast amounts of data in real time, allowing for even more precise and timely personalization.

Chatbots and virtual assistants are becoming increasingly sophisticated, providing personalised recommendations and customer support. Augmented reality (AR) and virtual reality (VR) technologies offer immersive experiences, allowing customers to virtually try products before making a purchase decision.

Moreover, the rise of Internet of Things (IoT) devices enables brands to gather data from various touchpoints, including wearables and smart home devices. This interconnected ecosystem opens up new possibilities for personalisation for retail, allowing brands to deliver seamless, personalised experiences across different platforms and devices.

Conclusion

Personalisation for D2C marketing has become a powerful tool. By utilising data and advanced analytics, brands can tailor their marketing efforts to meet the unique needs and preferences of individual customers. This personalised approach allows brands to create meaningful connections, drive business growth, and provide exceptional customer experiences. The future of personalisation in D2C marketing holds great potential, as brands can leverage emerging technologies to stay ahead of consumer expectations and unlock new opportunities for personalisation. By incorporating personalisation into their strategies, brands can boost visibility, engagement, and loyalty, ultimately leading to long-term success in the competitive D2C marketplace.