Predictive Audiences provide marketers with highly valuable audience groups based on consumers’ predicted actions, preferences, and lifetime value. These audiences allow more targeted sends to distinct groups of shoppers, maximizing engagement and conversion rates, while optimizing the amount of communication per shopper. These models are continuously refined, as Bluecore predictions use terabytes of unique data to make models better, faster, and more accurate every day. Use Predictive Audiences to find your next-best shoppers to grow, retain, win back, and optimize revenue.
Our core models include:
Though calculated in different ways with different logic, each predictive filter utilizes predictive analytics and data science algorithms to calculate a score for every shopper.
NOTE: These scores are refreshed and recalculated on a overnight as new data is made available.
1. PREDICTED CUSTOMER LIFETIME VALUE
Predicted Customer Lifetime Value (PCLV) predicts the amount a customer will spend over the course of their relationship with your brand. Customers are filtered into percentiles according to their predicted lifetime spend.
Bluecore’s calculation is predicted unlike other Customer Lifetime Value (CLV) models which may only take a customer’s past purchase behavior into account, which also includes non-buyers who haven’t yet made a purchase. Our calculations can identify potentially high value non-buyers who resemble your highest spending customers based on other online signals, such as frequency of visits, time from sign up, and products browsed.
EXAMPLE CAMPAIGNS
You may use a PCLV audience to:
Nurture your highest value shoppers: Send exclusive news and promotions on new or back-in-stock products.
Build loyalty of highest potential shoppers: Send continuous and relevant communication on categories of interest.
Identify potential VIP shoppers: Promote your loyalty program with exclusive access and promotions.
Discover more shoppers like your top shoppers: Use this group as a seed for lookalike audiences on Google, Facebook etc., to discover new, high-value shoppers.
Optimize multi-channel engagement: Narrow your audience on paid media channels (such as Facebook and Google Adwords) to highest value shoppers.
USING PCLV IN BLUECORE
To filter customers based on PCLV, select Top, Between, or Bottom and enter the percentile or range you want to target.
When you enter a percentile or range, the graph will show the average predicted CLV and the approximate number of customers available for the filter.
Select the checkbox to include customers with an unknown Customer Lifetime Value. A customer has an unknown Customer Lifetime Value if Bluecore does not have enough data about the customer.
2. LIFECYCLE STAGE
Lifecycle Stage predictions find customers based on which of four buying cycle stages they fall into:
A. Non-Buyers
D. Lost Buyers
These audiences can be used for lifecycle stage-based campaigns, such as turning non-buyers into buyers, or targeting at-risk customers.
NOTE: Lifecycle models look back 4 years.
Bluecore’s models are predictive, and not based on static time-based rules. For example, other lifecycle models may define a shopper as at-risk if they haven’t purchased in 90 days, or define them as ‘lost’ if they haven’t purchased in 120 days. These hard rules may result in delayed, infrequent, or just inaccurate targeting of shoppers in various lifecycle stages. In contrast, Bluecore’s predictive model analyzes the change in each shopper’s individual purchase cadence over time, comparing to similar shoppers to make designations such as at-risk. For example, monthly and quarterly purchasers would be assessed differently based on their unique purchase history patterns.
A. NON-BUYERS
Non-Buyers are customers who have not made a purchase on your site yet, and can be filtered based on when identified.
NOTE: Because lifecycle models look back 4 years, it's possible a shopper had purchased prior to the last 4 years. However, within the last 4 years, they are considered a non-buyer.
EXAMPLE CAMPAIGNS
You may use a non-buyers audience to target newly identified shoppers to aim for first conversion, via email, SMS, or paid media channels (Facebook, Google, etc.). Consider combining with a High PCLV filter to target your highest potential shoppers, especially if offering a welcome discount.
USING NON-BUYERS IN BLUECORE
You can choose to filter for all Non-Buyers by selecting the main Non-Buyers checkbox. To filter for Non-Buyers who joined the audience segment within a specific timeframe, select the Became a Non-Buyer in the last checkbox and enter a number for the number of days for your timeframe.
TIP: This is set to seven days by default. Be sure to configure a timeframe that corresponds with the campaign that this audience is being used in.
NOTE: The date somebody becomes a Non Buyer is the day they make their first view on the website, so this filter remains at 7 days, you're essentially targeting customers who 1) viewed a product in the last 7 days 2) haven't purchased in the last 4 years.
B. ACTIVE BUYERS
Active Buyers are shoppers who have made a purchase within their typical buying cycle. Each shopper’s typical buying cycle is determined uniquely, such as purchasing once every two weeks, or purchase once every six months.
EXAMPLE CAMPAIGNS
You may use an Active Buyers audience to:
Convert one-time buyers into repeat purchasers: Target next best recommendations via email, followed by a social media campaign to translate the first purchase moment into an ongoing brand relationship.
Engage and reward repeat purchasers: Send regular product announcements, loyalty discounts, or insider news to engage active buyers. Consider combining with a category affinity audience to target shoppers based on product-based affinities (such as shoes vs. outerwear shoppers).
USING ACTIVE BUYERS IN BLUECORE
Filter for all Active Buyers by selecting the main Active Buyers checkbox. To further filter Active Buyers, select a type of Buying Behavior: All buyers, One-time buyers, or Repeat buyers. To filter for Active Buyers who joined the audience segment within a specific timeframe, select the Became an Active Buyer in the last checkbox and enter a number for the number of days for your timeframe.
TIP: This is set to seven days by default. Be sure to configure a timeframe that corresponds with the campaign that this audience is being used in.
C. AT-RISK BUYERS
At-Risk Buyers are shoppers who have deviated from their typical buying cycle and are at risk of never purchasing again. This is determined based on each customer’s unique buying cycle, such as a two week buying cycle or six month buying cycle. As customers can become at-risk buyers after varying time periods, this filter will find at-risk buyers more accurately than rule-based approaches.
EXAMPLE CAMPAIGNS
You may use an at-risk buyers audience to:
Run promotional winback campaigns to save at-risk buyers from being lost to your brand: Offer a We miss you! discount code. Consider combining with a discount affinity audience for further targeting.
Re-engage at-risk shoppers: Send promotional marketing around new releases. Combine with a category affinity audience for further targeting based on inferred product preferences. Run parallel re-engagement campaigns targeting at-risk shoppers on paid media channels (such as Criteo or Google) for raised awareness.
USING AT-RISK BUYERS IN BLUECORE
Filter for all At-Risk buyers by selecting the main At-Risk Buyers checkbox. To further filter At-Risk buyers, select a type of Buying Behavior: All buyers, One-time buyers, or Repeat buyers. To filter for At-Risk buyers who joined the audience segment within a specific timeframe, select the Became At-Risk in the last checkbox and enter a number for the number of days for your timeframe.
TIP: This is set to seven days by default. Be sure to configure a timeframe that corresponds with the campaign that this audience is being used in.
D. LOST BUYERS
Lost Buyers are customers who have a high probability of never purchasing from your site again based on having already exceeded their typical buying cycle behavior, such as having already made their once every six months purchase which exceeds the threshold of their typical buying cycle. Customers can become lost buyers after varying time periods, depending on their unique purchase history pattern.
EXAMPLE CAMPAIGNS
You may use a Lost Buyers audience to:
Offer an aggressive winback/next purchase discount. Combine with a discount affinity filter.
Encourage a more regular purchase cadence through targeted product marketing. Run a recommendations-focused campaigns in a post-purchase flow, While you’re here, you may also be interested in… Combine with a category preference filter.
USING LOST BUYERS IN BLUECORE
You can choose to filter for all Lost Customers by selecting the main Lost Buyers checkbox. To further filter Lost Buyers, select a type of Buying Behavior: All buyers, One-time buyers, or Repeat buyers. To filter for Lost Customers who joined the audience segment within a specific timeframe, select the Became Lost in the last checkbox and enter a number for the number of days for your timeframe.
TIP: By default, this is set to seven days. Be sure to configure a timeframe that corresponds with the campaign that this audience is being used in.
3. LIKELIHOOD TO TAKE ACTION / CHANNEL PREFERENCE
The Likelihood to Take Action models predict whether a customer will unsubscribe from emails, open an email, click an email, or convert (make a purchase in the next 14 days). These models are simple to action since they build off all the website and email/ SMS engagement data that Bluecore collects.
EXAMPLE CAMPAIGNS
You may use a Likelihood to Take Action audience to:
Optimize list size by limiting additional/follow-up on communications to those least likely to opt-out: Include a low likelihood to unsubscribe filter on batch communications, or within additional touchpoint trigger notifications to prevent unsubscribes resulting from over-communication.
Prioritize audiences for paid media channels: Send high likelihood to unsubscribe audiences to Facebook or Google to continue sending advertisements while not getting hit with an opt-out penalty on email or SMS.
Optimize spend in a channel: Limit communication on SMS to shoppers with a high channel preference for SMS.
Optimize for engagement and/or conversion in batch campaigns: Applying a high likelihood to convert, high likelihood to click an email, or high likelihood to open an email filter targets communication to the most engaged audiences, who value constant engagement.
USING LIKELIHOOD TO TAKE ACTIONS IN BLUECORE
For each action, filter for customers who have a low, medium, or high likelihood to take the corresponding action.
When you add likelihood filters, the pie chart in the top right corner of each section will display the number of customers available for that filter.
USING CHANNEL PREFERENCE IN AUDIENCE BUILDER
Bluecore’s Channel Preference model is an extension of the Likelihood to Take Action models, using email and SMS engagement data to predict a shopper’s preferred channel for communication.
See the Email or SMS Channel Preference article for further details on the Channel Preference model and feature usage.
4. PRODUCT PREFERENCES
Product Preferences predict the products customers will be interested in buying based on their observed preferences for specific categories (Category Preference) or the probability of requiring a discount to make a purchase (Discount Preference) or the probability they will replenish a purchase (Replenishment Preference). Models include:
A. HIGHEST CATEGORY PREFERENCE
The highest category preference tool is used to input product, brand, or category affinities in a ranked order. Unlike category, discount, and replenishment preference, highest category preference must be configured outside of Audience Builder. Configure an audience for highest category preference by following the instructions outlined in this article. Once the affinity group has been configured, add it to an audience in Audience Builder by using the highest category product preference section, as shown below:
EXAMPLE CAMPAIGNS
Highest category preference audiences are most useful when sending campaigns to mutually exclusive groups of shoppers based on the preference for certain product categories. Use highest category preference audiences to:
Customize batch campaigns by shopper preferences for distinct product categories: Shoppers who are interested in shoes vs. shoppers who are interested in accessories
Segment new arrivals campaigns by varying shopper interest
Target holiday-related campaigns to shoppers who appear most interested and receptive. Sending non-holiday themed campaigns to shoppers in other preference groups
B. CATEGORY PREFERENCE
Category Preference predicts the shopper’s preference for specific product categories. Bluecore’s model uses a range of behavioral data beyond just past purchases and views by associating it with email addresses (instead of just anonymous pixels), to target customers consistently across marketing channels. Bluecore’s model includes co-view, co-purchase, and co-cart data (for collaborative filtering models, such as, customers who viewed this also tend to view that) to discover relationships between products and categories that may not be immediately obvious. For example, if someone buys a TV we’ll know they have a certain level of affinity to a sound system.
EXAMPLE CAMPAIGNS
You may use a category preference audience to:
Run a remarketing campaign for a product line: Narrow the target audience to shoppers most interested in that particular product line. Run this campaign parallel on paid media channels (Google, Facebook, etc.) for maximized awareness.
Market new arrivals to shoppers most interested in that product or category.
Find more shoppers with affinity to a particular product category: By using this audience as a seed for lookalike audience campaigns on paid media channels (Google, Criteo, etc.)
Cultivate loyal shoppers by targeting based on an affinity to certain product categories. Combine with a high likelihood to convert filter.
Run targeted holiday campaigns: Only send a campaign to shoppers who have shown an affinity to Valentine’s Day (or other holidays) related products for a targeted campaign.
USING CATEGORY PREFERENCE IN BLUECORE
Use the Add category filter drop-down to select the categories by which customers should be filtered. Then, use the slider to select a preference level for the selected category.
C. DISCOUNT PREFERENCE
Discount Preference predicts a shopper’s affinity to buying products at full price or discounted and to what extent. Bluecore’s model uses both browse and purchase data (calculated using a weighted average model preference purchase history). This surpasses other models which may just look at past purchase behavior, which may exclude non-buyers. With this model, treat full price and discount buyers separately, allowing you to maintain margin and maximize revenue.
EXAMPLE CAMPAIGNS
You may use a discount preference audience to:
Run retention-focused promotional campaigns: Target shoppers who have shown an affinity to a discount in order to convert. Preserve your margin by not sending sales or discount codes to shoppers who don’t require them. Run a retention campaign on paid social media channels in parallel.
Run campaigns for premium products to a targeted audience: Send full-price related campaigns to full-price buyers, treating them separately from discount buyers.
USING DISCOUNT PREFERENCE IN BLUECORE
Discount Preference predicts the customer’s preference to be a Discount Buyer, a Full Price Buyer, have No Preference, or has a preference that is Unknown. Select the preference designation(s) for which to filter. A customer will have an unknown preference if we do not have enough data.
D. REPLENISHMENT PREFERENCE
Replenishment predicts which of your customers are replenishers. For example, those who have purchased a specific product or category in a pattern that implies replenishment, and the cadence on which they will want to purchase those products. The Bluecore model identifies replenishable products by tracking the purchases of shoppers showing replenishing behavior (a minimum number of repeat purchases over a period of time), and determining which of these products have a minimum number of replenishers. The model is now able to target replenishers at their dynamically calculated personal replenishment cadence, as well as identify potential new replenishers.
EXAMPLE CAMPAIGNS
You may use a replenishment preference audience to:
Message shoppers who are due for a replenishment: Give a nudge - It’s time to restock!, to replenishers who have a history of purchasing replenishable products. E.g. Filter to shoppers deemed eligible to replenish mascara within the last day and have bought the product more than once.
Cultivate shoppers who are buying a replenishable product for the first time: Aim to have shoppers buying the product on a regular cadence by messaging a replenishment campaign when they are eligible for one.
USING REPLENISHMENT PREFERENCE IN BLUECORE
Use the eligibility drop-down to select eligible customers. Use the frequency drop-down to filter customers based on how many times they have purchased the replenishable product. You can use additional filters to refine the targeted audience.
Check out Predictive Audiences Technical Overview for a more in-depth technical explanation of Bluecore's predictive audiences.