Breaking Down Machine Learning for Marketing Purposes

While the study of machine learning and artificial intelligence is quite broad, there are a handful of approaches to developing effective “learning” algorithms and approaches. Consider this a primer to get you started with a good understanding of current approaches and how they apply to your AI-based marketing efforts:

Supervised learning algorithms

These use properly labeled data sets to train an algorithm to make predictions. They’re great for classification, or labeling new data through a mapping function from input variables to discrete output variables. A classic use of supervised learning algorithms you can likely relate to is the classifying of emails as “spam” or “not spam” based on input variables leading to a discrete output variable (“spam” or “not spam”). A second major use of supervised learning is for regression analysis, in which the training data is used to map input variables to a continuous output variable—a real number or value, often quantities like amounts or sizes, within certain error boundaries to indicate the accuracy of the prediction.

Unsupervised learning algorithms

This category takes unlabeled sets of data with no known outcomes or results and is useful for discovering the underlying structure of the data. They are typically used for clustering data within sets, detecting anomalies (like fraudulent transactions), mining for associations (understanding what types of goods are on a typical retail receipt to better merchandise products on retail shelves), reducing the number of features in a given data set, or breaking out a data set into multiple, smaller sets for further analysis.

Semi-supervised learning algorithms

These use a combination of labeled and unlabeled data for training. Generally speaking, they rely on smaller labeled data sets that include outcome information used in conjunction with much larger unlabeled data sets. They’re used when you don’t have enough labeled data to produce an accurate model. With this approach, you can increase the size of your training data by applying this technique.

Reinforcement learning

This one of the newest approaches to machine learning. As the name indicates, a reinforcement algorithm learns by trial and error to achieve its objective. The machine tries out lots of different things and gets rewarded or penalized based on the outcomes of its behaviors and how well they help or hinder it from reaching its objective. Google’s AlphaGo used reinforcement learning algorithms to beat the best players in the world in the complex strategy game Go.

Deep learning

Architectures represent another, perhaps even more revolutionary, approach to AI-based application development—a field of data science that has also accelerated in recent years. They’re based on artificial neural networks (ANNs) and support a variety of learning approaches, including supervised, unsupervised, and semi-supervised. “Deep” refers to the number of layers through which data is transformed; in certain models, the number of transformations is fixed, and in others, known as recurrent neural networks, the number of transformations is potentially infinite. These architectures are among the most exciting in data science today and have been applied successfully to drug design, bioinformatics, social network filtering, speech recognition, computer vision, natural language processing, machine translation, audio recognition, material inspection, medical image analysis, and board game programs. In many cases, they’ve produced results comparable to or even superior to human subject-matter experts.

As you can see in Figure 5-1, many of the different approaches to machine learning described here can be applied to different applications related to marketing automation. Each application represents an order of magnitude leap from the conventional, manual approaches of days gone by thanks to the availability and sheer volume of data that we can now feed into these algorithms.

The “x” factor is deep learning, which cuts across the four major approaches to machine learning. This approach can be incorporated where the benefits of this more computationally intensive method outweigh the more lightweight methods of classical machine learning approaches.

Figure 5-1. The different types of machine learning

Major Type of Unsupervised Learning Algorithms

There’s only one major variety of unsupervised learning algorithm that we’re going to address here: k-means.

Learning Algorithms That Can Be Supervised or Unsupervised

The learning algorithms can either be supervised or unsupervised using the following popular machine learning methods.

Decision Tree

Just as the name implies, a decision tree can be described as a support tool that uses a tree-like model (Figure 5-2) in reaching decisions and also determining their possible consequences such as outcomes, utility, and cost of resources. It serves as one of the most effective ways of displaying algorithms containing conditional control statements. A decision tree shares the same features as a flowchart where each internal (non-leaf) node is used to represent a test on a parameter, branches represent the test outcome, and leaves (or terminal) serve as a class label. These trees can serve as an integral part of operation research in decision analysis and play an important role in identifying a strategy that is most likely to reach a goal.

There is no denying the fact that businesses have to deal with lots of data obtained from market, competition, and customer analysis. Dealing with this data effectively to reach the right conclusion may take longer than expected, thus causing a delay. Since identifying and proffering solutions to business problems can be time consuming for most executives or managers, the use of decision trees can provide them with a simple abbreviated method of predicted outcomes for each of the split trees. A decision tree is a visual representation of the decision-making process and can be used to simplify problems as different as credit card attrition and currency exchange rates.

Figure 5-2. An example of a decision tree diagram using flowchart symbols

Random Forest

Using several decision trees to determine the final result and predict possible outcomes can be better than using a single decision tree. A single tree cannot make a forest, and that’s why random forest (random decision forest algorithm) is the preferred method for regression, classification, and other tasks that need to construct a lot of decision trees during training time and release the class mode or mean prediction of these trees.³ (See Figure 5-3 for an illustration of how random forest works.)

Random forest is often used by many companies to make predictions with a process concerning machine learning. It uses multiple decision trees aimed at making a more holistic analysis of a given data set. During analysis, the random forest can build on the decision tree model and make the entire process more complicated. Most experts are of the view that these random forests represent “stochastic guessing” or “stochastic discrimination.”

A random forest algorithm can be used to test the quality of a customer growth strategy or product quality; for example, it has been used by companies to determine the quality of wine through parameters like alcohol content, sulfur dioxide level, pH, acidity, and sugar content. It can also be utilized in taking various product properties and variables to indicate the interests of customers and how best to meet their needs.

In many business settings, a random forest algorithm takes note of the random subset features for each tree and determines the most probable outcome. In this way a multitude of evaluations can be performed and the most likely outcome used to predict success.

Before using the random forest algorithm, I advise that you first isolate the predictive data utilized during production and apply it to the random forest model while using a certain set of training data.

Figure 5-3. An example of a random forest simplified diagram

The Importance of Data

The most important rule to remember is that data is what powers algorithms—it’s the fuel that fires up the AI machine. So what happens when the data used to train machines is flawed? Many data scientists and others building next generation AI solutions actually spend a good amount of time scrubbing the data, cleaning it up, and putting it into a format computers can actually use. If you put garbage in, then you’ll get garbage out.

The most important rule to remember is that data is what powers algorithms—it’s the fuel that fires up the AI machine.

The best way to get clean data is to set up the right API connections from all of your key data sources and pipe them into your AI intelligent machine.⁴ At IMVU, we have the following data sources that were connected via API to our AI intelligent machine called Athena Prime:

• AppsFlyer, which is our mobile attribution and marketing analytics platform. This is our source of truth for measuring success from our mobile user acquisition campaigns from different partners, including Google, Facebook, Snapchat, Apple Search, Instagram, Liftoff, InMobi, and many more. AppsFlyer, like most other attribution solutions in the space, is integrated with all the major mobile ad networks and partners so it’s seamless to track all these campaigns in one place. We also pass back all our key CRM downstream event data like new payers, revenue, and engagement. This enables AppsFlyer to pass all this valuable data back to all our advertising partners to enable them to build lookalike user segments for our systems to target on those different partner networks.

• Leanplum is our marketing automation and CRM platform. We pass our cross-platform data into Leanplum from our backend data warehouse to help us create customized on-boarding, retargeting, and reengagement campaigns to help us better engage, retain, and monetize our users. Our goal is to ensure all new users follow similar user journeys to replicate our best lifetime value customers by influencing them to take the same user actions and behaviors.

• All the paid user acquisition channels—Facebook, Google, Snapchat, Apple Search, Liftoff, InMobi, and many others—are connected to pass their data back to enable us to control the optimization levers like budgets, bids, and goals.

• Creative assets are developed by the marketing team in-house at IMVU, based on an ongoing analysis of what’s working and what’s creating the most value within any given market segment. Creatives are added to each marketing channel for automated distribution.

These elements are all feeders into Athena Prime (which is the “intelligent machine” used by IMVU); we can turn over customer segments for targeting, channels for promotion, and creative elements to Athena to drive our desired marketing outcomes with maximum efficiency.

Athena Prime starts with our base business needs for any given campaign, such as marketing objective, creatives to be used within a campaign, and any additional constraints (budget, campaign dates, etc.). These parameters are fed into Athena using the UI or through programmatic API calls, providing the instructions or marching orders for the system.

As a Software as a Service (SaaS) platform, Athena Prime abstracts key components of digital media campaigns:

• Business Needs (campaign configuration) from Audience Selection, Message Placement

• Performance Optimization (i.e., campaign orchestration, contained in the large box below)

• Reporting on Business Outcomes (meeting business goals, performance insights on aggregate audiences included in a campaign, and any insights into how content or ads performed)

In a generic framework sense, you can view an intelligent marketing machine in Figure 5-4, with the classes of machine learning algorithms written in white.

Figure 5-4. The intelligent machine framework

Audience Selection

In terms of Audience Selection, Athena Prime uses natural language processing, neural processing, and deep learning models to analyze ad copy and landing pages to extract interest-based targeting parameters to the extent they are made available by participating channels to improve ad relevance and performance. This feature, dubbed “Athena Sense,” does not allow for targeting on an individual level, but instead adds a contextual or interest-based component to campaign targeting without any human intervention. Athena Sense may add hundreds of additional interest-based targeting parameters to any given targeting set—something that would require an inordinate amount of work by employees or agencies to attain that level of targeting detail.

These interest-based targeting parameters are provided by platform/channel partners via programmatic APIs. These interest-based, behavioral, or demographic targeting parameters are identical to those available directly within the corresponding platform’s user interface.

For example, Athena Sense may identify that a particular ad in a campaign makes reference to Game of Thrones. Figure 5-5 shows how this targeting parameter is made available in the Facebook user interface.

Figure 5-5. A targeting parameter in the Facebook UI

Instead of an agency or team member working through the UI of five or more marketing channels, Athena enhances targeting intelligently and automatically. This saves time, improves performance, and generates higher return on our marketing spend.

It’s also interesting to note that features like Athena Sense—which extracts meaning and context from creatives and landing pages—add valuable targeting insights that are used by the marketing platform AI on the other side of the handshake. These clues are so valuable that platforms like Facebook and Google reward advertisers that add detailed targeting enhancements to their campaigns, further boosting performance and ROI.

Message Placement

This functionality includes features that take ad creatives or “content” and configure them for use on various channels, and as such, don’t take into account audience targeting on any granular level beyond placement availability or relevance.

Exploration and Optimization

The final component of Athena Prime is an optimization engine that makes campaign adjustments based on performance. Athena Prime observes results being reported programmatically across channels to shift budgets to ensure maximum efficiency. This may involve shifting budgets away from certain audience segments or increasing budgets against others. It may also shift budget between different channels based on current performance against goals. But in no case does this optimization engine deal with performance on an individual user basis.

Applying Machine Learning and AI to the Customer Journey for IMVU

IMVU analyzed user journeys with our data team to explore what organic behaviors resulted in the most valuable users or purchasers. One key insight became very clear: if we can get someone to make an in-app purchase within the first seven days, this is a significant indicator of higher lifetime value. In addition, users interacting with different features and exhibiting certain behaviors within IMVU proved to be good indicators of what leads to a purchase. Our goal was to find ways to increase customer LTV and create incremental lift over organic purchases (LTV will explored in further depth in Chapter 7).

To put the insights from this study to work, we segmented our customers into three primary groupings:

• People who installed the app, but didn’t register

• People who were on a “First Seven Days” journey

• Lapsed purchasers

Taking the insights from our user journey study, the marketing team then created a host of creatives for each segment grouped by where they appeared to be in their user journey. The “winners” for IMVU at each stage in the sequence are shown in Figure 5-6.

Figure 5-6. IMVU user journey creative sequence for different segments by day

Artificial Intelligence

Let’s review the business processes at play and how the application of AI drives meaningful optimizations and outcomes through large-scale experimentation.

Starting with IMVU’s overall strategy, we set our objectives (desired outcomes), creatives, and any other campaign constraints. We then get segmentation data from our data warehouse and CRM sources, along with custom audiences we’ve developed over time. AI automates blending segmentation models with cross-channel message placement, which automatically explores, observes, and optimizes for the right business outcomes. From there, we seek further potential audience or creative insights, update our approach, and the cycle goes on. Figure 5-7 shows an example of an IMVU split test of thousands of different creative variables across different segments.

Figure 5-7. IMVU example of testing different creative variables across different segments

Findings

For our lapsed purchasers segment—defined as anyone who made an in-app purchase in the last 180 days but not in the last 30 days—we learned that there were two kinds of content that worked best:

• As a user-generated platform, IMVU benefits from an evergreen pipeline of amazing content created by its members (similar to YouTube or Soundcloud). The firm found that highlighting content from IMVU’s most influential creators delivered a showcase of novel products from the best of IMVU’s creators.

• Weekly contests, in which users can participate to win free credits as you see in Figure 5-8, proved very popular and did a great job of attracting lapsed users back both to participate and purchase again.

We also learned that our Day 1 users were motivated by a simple message: reminding them that they can redeem free credits to get started, as you can see in Figure 5-9. This engaged them in the app and encouraged them into the flow of becoming a high lifetime value customer.

Figure 5-8. An example of the IMVU weekly contest Facebook ad

Figure 5-9. IMVU example of a retargeting ad to remind users to redeem their free credits

Bringing It All Together

Scaling growth doesn’t come easy. Let this be your road map to maximizing your customer LTV by always running sequential tests for different cohorts at different stages throughout the entire user journey. To turbocharge your performance, consider working with (or building) an intelligent AI machine to help you automate key levers like blending segmentation models with cross-channel creative placements, achieving data-driven results far beyond manual capabilities.

Now that we’ve got the basics of AI as they’re applied to marketing, and an understanding of customer life cycle marketing, we can explore options around building or buying a solution to help you turbocharge your startup’s growth.