CBPO

Tag: predictive

New predictive capabilities in Google Analytics

April 20, 2021 No Comments

Google Analytics helps you measure the actions people take across your app and website. By applying Google’s machine learning models, Analytics can analyze your data and predict future actions people may take. Today we are introducing two new predictive metrics to App + Web properties. The first is Purchase Probability, which predicts the likelihood that users who have visited your app or site will purchase in the next seven days. And the second, Churn Probability, predicts how likely it is that recently active users will not visit your app or site in the next seven days. You can use these metrics to help drive growth for your business by reaching the people most likely to purchase and retaining the people who might not return to your app or site via Google Ads.

Reach predictive audiences in Google Ads

Analytics will now suggest new predictive audiences that you can create in the Audience Builder. For example, using Purchase Probability, we will suggest the audience “Likely 7-day purchasers” which includes users who are most likely to purchase in the next seven days. Or using Churn Probability, we will suggest the audience “Likely 7-day churning users” which includes active users who are not likely to visit your site or app in the next seven days.

crop2_predictive_audience_suggested@2x.png

In the Audience Builder, you can select from a set of suggested predictive audiences.

In the past, if you wanted to reach people most likely to purchase, you’d probably build an audience of people who had added products to their shopping carts but didn’t purchase. However, with this approach you might miss reaching people who never selected an item but are likely to purchase in the future. Predictive audiences automatically determine which customer actions on your app or site might lead to a purchase—helping you find more people who are likely to convert at scale.

Imagine you run a home improvement store and are trying to drive more digital sales this month. Analytics will now suggest an audience that includes everyone who is likely to purchase in the next seven days—on either your app or your site—and then you can reach them with a personalized message using Google Ads.

Or let’s say you’re an online publisher and want to maintain your average number of daily users. You can build an audience of users who are likely to not visit your app or site in the next seven days and then create a Google Ads campaign to encourage them to read one of your popular articles.

Analyze customer activity with predictive metrics

In addition to building audiences, you can also use predictive metrics to analyze your data with the Analysis module. For example, you can use the User Lifetime technique to identify which marketing campaign helped you acquire users with the highest Purchase Probability. With that information you may decide to reallocate more of your marketing budget towards that high potential campaign.

predictions2 (1).gif

View the Purchase Probability of users from various marketing campaigns.

You will soon be able to use predictive metrics in the App + Web properties beta to build audiences and help you determine how to optimize your marketing budget. In the coming weeks these metrics will become available in properties that have purchase events implemented or are automatically measuring in-app purchases once certain thresholds are met.

If you haven’t yet created an App + Web property, you can get started here. We recommend continuing to  use your existing Analytics properties alongside an App + Web property.


Google Analytics Blog


6sense raises $125M at a $2.1B valuation for its ‘ID graph’, an AI-based predictive sales and marketing platform

March 30, 2021 No Comments

AI has become a fundamental cornerstone of how tech companies are building tools for salespeople: they are useful for supercharging (and complementing) the abilities of talented humans, or helping them keep themselves significantly more organised; even if in some cases — as with chatbots — they are replacing them altogether. In the latest development, 6sense, one of the pioneers in using AI to boost the sales and marketing experience, is announcing a major round of funding that underscores the traction AI tools are seeing in the sales realm.

The startup has raised $ 125 million at a valuation of $ 2.1 billion, a Series D being led by D1 Capital Partners, with Sapphire Ventures, Tiger Global and previous backer Insight Partners also participating.

The company plans to use the funding to expand its platform and its predictive capabilities across a wider range of sources.

For some context, this is a huge jump for the company compared to its last fundraise: at the end of 2019, when it raised $ 40 million, it was valued at a mere $ 300 million, according to data from PitchBook.

But it’s not a big surprise: at a time when a lot of companies are going through “digital transformation” and investing in better tools for their employees to work more efficiently remotely (especially important for sales people who might have previously worked together in physical teams), 6sense is on track for its fourth year of more than 100% growth, adding 100 new customers in the fourth quarter alone. It caters to small, medium, and large businesses, and some of its customers include Dell, Mediafly, Sage and SocialChorus.

The company’s approach speaks to a classic problem that AI tools are often tasked with solving: the data that sales people need to use and keep up to date on customer accounts, and critically targets, lives in a number of different silos — they can include CRM systems, or large databases outside of the company, or signals on social media.

While some tools are being built to handle all of that from the ground up, 6sense takes a different approach, providing a way of ingesting and utilizing all of it to get a complete picture of a company and the individuals a salesperson might want to target within it. It takes into account some of the harder nuts to crack in the market, such as how to track “anonymous buying behavior” to a more concrete customer name; how to prioritizes accounts according to those most likely to buy; and planning for multi-channel campaigns.

6sense has patented the technology it uses to achieve this and calls its approach building an “ID graph.” (Which you can think of as the sales equivalent of the social graph of Facebook, or the knowledge graph that LinkedIn has aimed to build mapping skills and jobs globally.) The key with 6sense is that it is building a set of tools that not just sales people can use, but marketers too — useful since the two sit much closer together at companies these days.

Jason Zintak, the company’s CEO (who worked for many years as a salesperson himself, so gets the pain points very well), referred to the approach and concept behind 6sense as “revtech”: aimed at organizations in the business whose work generates revenue for the company.

“Our AI is focused on signal, identifying companies that are in the market to buy something,” said Zintak in an interview. “Once you have that you can sell to them.”

That focus and traction with customers is one reason investors are interested.

“Customer conversations are a critical part of our due diligence process, and the feedback from 6sense customers is among the best we’ve heard,” said Dan Sundheim, founder and chief investment officer at D1 Capital Partners, in a statement. “Improving revenue results is a goal for every business, but it’s easier said than done. The way 6sense consistently creates value for customers made it clear that they deliver a unique, must-have solution for B2B revenue teams.”

Teddie Wardi at Insight highlights that AI and the predictive elements of 6sense’s technology — which have been a consistent part of the product since it was founded — are what help it stand out.

“AI generally is a buzzword, but here it is a key part of the solution, the brand behind the platform,” he said in an interview. “Instead of having massive funnels, 6sense switches the whole thing around. Catching the right person at the right time and in the right context make sales and marketing more effective. And the AI piece is what really powers it. It uses signals to construct the buyer journey and tell the sales person when it is the right time to engage.”


Enterprise – TechCrunch


Five ways to use predictive analytics

May 29, 2018 No Comments

The era of graphs and spreadsheets as a way of thinking about analytics is beginning to approach its end. Predictive analytics, along with associated artificial intelligence (AI) and machine learning technologies, are changing the way in which we deal with data. These tools are becoming more accessible, and ‘big data’ thinking is no longer limited to firms with billion dollar budgets.

Predictive analytics provides a glimpse into the future, as well as access to strategic insights that can open up new opportunities. Here are five ways you can put predictive analytics to use, and how you can change the way you think about data.

Qualifying leads

According to Forrester research, predictive analytics has found three main use cases for dealing with  leads. Specifically:

  1. Predictive scoring: This method analyzes how leads are responding to your marketing attempts and how likely they are to take action based on that information. In this way, you can more quickly identify which leads to focus more resources on and which to divert resources from.
  2. Identification models: This use case is an approach that focuses on comparing leads to customers who have taken actions in the past. In doing so, you can divert resources to those leads who are most promising based on previous actions they have taken, as well as identify new markets that you weren’t previously aware of.
  3. Personalization: In concert with predicting which leads are most likely to take which actions, the same data can be used to determine which leads respond best to which types of messaging. This advanced form of segmentation can take things deeper than simply splitting leads into groups – instead sending them much more personalized messages.

One prominent example of this was covered in the Harvard Business Review, detailing how a Harley Davidson dealership increased sales leads by 2930% using an AI named Albert.

The AI crunched CRM data to identify characteristics and behaviors of previous buyers. It then split them into micro-segments based on those characteristics. For each segment, it tested different combinations of headlines, visuals, and other elements to determine which worked best for each segment.

The value of your lead qualification is highly dependent on the value and quantity of your data. No matter how good your statistical models are, their abilities are still very limited without access to the information that they need to learn about your customers.

In the digital space – particularly if you are not using a CRM – the best place to start with predictive analytics will almost certainly be an integration of Google Analytics and Google BigQuery.

Modeling customer behavior

While lead qualification and conversion is the most obvious use-case for predictive analytics, and likely the one worth looking into first, it’s far from the only marketing application of this emerging technology. But virtually any use is going to have customer modeling at its core.

You can divide customer modeling into three basic types: cluster models, propensity models, and collaborative filtering.

Cluster models

Clustering is a way of segmenting customers into groups based on many variables. A cluster model looks for correlations between various attributes and identifies a number of equilibria in which certain types of attributes tend to accumulate. What makes clustering special, compared with traditional segmentation, is the sheer number of variables involved. Clusters often use 30 variables or more, far more than would be possible if you were manually segmenting customers, or even if they were manually segmenting themselves.

Clusters come in three forms:

  1. Product clusters: These are clusters of customers who tend to only buy specific types of products, ignoring other things in your catalog
  2. Brand clusters: These customers tend to buy from a specific collection of brands
  3. Behavioral clusters: These are segments of customers with a specific collection of behaviors, such as frequent buyers who place small orders, or customers who prefer the call center over the checkout cart.

What’s important to recognize about these clusters is that they enable predictions about which clusters people belong to – even with limited information. If they buy one product with a specific brand, your brand cluster can predict what other brands they may be interested in, rather than just the more obvious recommendation of simply offering everything else by the same brand.

Propensity models

A propensity model is one that makes future predictions about customer behavior based on correlations with other behaviors and attributes. This may be accomplished using regression analysis or machine learning. A good propensity model controls for as many variables as possible so that correlations aren’t confused for causes.

Here are a few examples of propensity models:

  • Propensity to unsubscribe: A model like this allows you to determine the appropriate email frequency, weighing the possibility that a recipient will unsubscribe against any possible positive outcome
  • Propensity to churn: These are customers who are likely to move on if you don’t take action, but who may be high value otherwise
  1. Lifetime value: Modeling the lifetime value of a customer can help you make strategic marketing decisions if it leads you to customers with more lifetime value, or leads to behaviors that extend lifetime value.

Other propensity models include predicting how far through somebody’s lifetime value you are, and how likely they are to convert or buy.

Collaborative filtering

If you’ve seen Amazon’s “customers who liked this product, also liked…” recommendations, you know what type of model this is. At first glance collaborative filtering might sound similar to product-based cluster models, but collaborative filtering is a bit different. Rather than grouping customers by the types of products they are likely to buy, collaborative filters make recommendations based on aggregate behavior.

In other words, this is less about the user’s product preferences and more about the behaviors that products tend to cause for users.

There are three types of collaborative filters:

  1. Up-sell recommendations. These are recommendations for a higher tier version of a product before the sale is made
  2. Cross-sell recommendations. Also offered before the sale is made, this is a recommendation for a product that is often bought at the same time as the initial one
  3. Follow-up recommendations. These are recommendations for products that people tend to buy a certain time period after buying a prior product, such as replacing a product that runs out, or buying dishes after buying a table.

Connecting the right product to the right market

Working backwards from customer modeling, it’s possible to identify markets for your products that you may not have been aware of. Here are just a few examples of how this use case can play out:

  • Incorporate referral sources into your cluster models. This will allow you to identify which traffic sources correlate with which types of products, brands, or behaviors. From this, you can immediately identify a new market for these products or brands
  • Incorporate referral sources into your lifetime value propensity models. This will allow you to determine which locations to invest more of your marketing resources into, since you roughly know what the ROI will be
  • Look for correlations between traffic sources and success with up-sells, cross-sells, and follow-up recommendations
  • Look for correlations between keywords and your customer models
  • Analyze the attributes that are strong predictors of buying specific types of products and brainstorm other markets that might share those attributes that you have not yet targeted
  • Investigate high performing outliers where limited data is available and investigate whether expanding in those markets is a good option.

Connecting the right users to the right content

There are a number of ways that you can leverage your customer models to connect prospects with content in ways that move you toward your goals, some of them more obvious than others. Here are a few examples:

  • Matching content related to products or brands based on the appropriate clusters
  • Matching users to conversion copy when propensity models predict they are most likely to buy
  • Recommending content to users that improves their propensity scores
  • Recommending content to users that enhances their likelihood of responding well to an up-sell or cross-sell
  • Matching traffic sources to the content that tends to produce high propensity scores for each particular traffic source.

As you can see, the number of approaches you can take here grows pretty quickly. Think strategically about how best to put your models to use and make the most of your models.

Discovering strategic marketing insights

While some predictive analytics tools can automatically streamline your marketing process and generate results (like Albert did for Harley Davidson), it’s important to remember that human decisions still play a very important part in the process.

Where predictive analytics and related AI tools often fail is in a propensity to ‘over-fit’ the data. They can get stuck at local maximums and minimums, incapable of making the leap to new terrain.

Escaping from traps like these, and making the most of these tools in general, requires you to find strategic insights from within your predictive analytics models.

For example, suppose you discover that a specific piece of content has a tendency to raise your prospects’ propensity scores; any automation you have in place can be applied to customize how your users are marketed to, and push them toward that piece of content. But what predictive analytics can’t tell you is whether there might be other traffic sources you haven’t tried yet that would be a good fit for that content. Using your experience and brainstorming capabilities, you can identify other potential markets for that content, feed them into your model, and see how the exposure changes things.

Your goal in working with these kinds of models must always be to find insights like these and test them to see if the results are as expected. If your model runs on autopilot it will not discover any new opportunities alone.

Search Engine Watch