Consumers today expect their interactions with various brands to be personalized, contextually relevant and responsive to their behaviors. Marketers must anticipate customer interests and intentions and decide on the next-best action. Blueshift’s customizable Predictive Intelligence utilizes the power of AI to help create 1:1 experiences and real-time interactions that adapt to each customer based on their data and behaviors. This helps marketers optimize who to target, with what content, on which channel, and at what time throughout the customer lifecycle.

Blueshift provides numerous standard out-of-the-box predictive models, including conversion, engagement, churn, and retention models. Blueshift also provides the flexibility for marketers to create their own custom predictive models that are tailored to meet their specific business requirements.

Blueshift also offers channel engagement predictive models to better understand a customer's propensity to engage in a specific channel. Blueshift provides channel engagement predictive models for the following channels: email, SMS, push, and in-app.

How does Blueshift’s predictive modeling work

Blueshift’s approach to predictive intelligence is to be fully transparent and customizable. You have full visibility into which user attributes and behaviors impacted the model the most and can track how the performance (i.e. conversion rate) of the predictive score changes over time. You can also customize models to your unique business requirements as required.

Blueshift’s AI-powered predictive models are trained on historical data to learn behavioral rules, which separate converting customers vs non-converting customers. Our platform then automatically derives customer behaviors from customer clickstream events and campaign engagements. Specifically, we derive hundreds of behaviors such as recency, frequency, time spent, catalog affinities (category affinity, brand affinity, product attribute affinity), etc for each event. These behaviors, along with user attributes, are referred to as features/variables and are fed into the AI model. The model then learns an optimal combination of features, which leads to conversion and a scoring function is learned.

Predictive models

Blueshift provides a number of out-of-the-box predictive models. It also provides the ability for you to create new predictive models and customize existing models based on business-specific goals via an easy-to-use interface.

Data analysis is automated and cleaning, de-duping, or normalizing of raw data is not required to get the training data ready or to remove noise from the models.

Predictive models, as well as the scoring against the models, are deployed and updated automatically as new data becomes available. Predictive scores are refreshed on the customer profile on a daily basis, whereas the predictive models are re-run and optimized on a weekly basis.

Blueshift's Predictive Intelligence provides the following capabilities.

Predictive recommendations

With Blueshift’s Recommendation Studio, recommendations automatically adapt to each customer in real-time based on their current activity, past behaviors and purchases, their affinities, and the latest catalog data. This ensures that recommended content is always relevant and engages your customers, known and anonymous. Product, content, and offer recommendations can be easily coordinated across all channels like email, push, SMS, websites, mobile apps, and more, to deliver a consistent brand experience.

Engage Time Optimization

Predictive Engage Time Optimization or Send Time Optimization, helps marketers to optimize send times for downstream behaviors that lead to revenue, rather than initial open rates. It takes into account that people today are much more likely to have many frequent bursts of activity around the clock. Predictive Engage Time Optimization uses AI to examine campaign clicks, website browsing behavior, total engagement time, engagement depth, and transactions to determine windows of time in which each customer is most likely to engage so that messages are sent to each customer at the best time accordingly.

Channel Affinity

The number of channels that you can use to interact with your customers is ever increasing. With various channels like, email, web, mobile, social, and so on, easily available, customers now switch seamlessly across multiple devices throughout the day, and channel engagement behaviors continue to evolve. Predictive Channel Affinity determines the best channel to engage each customer by using AI to learn on which channel each individual customer is most likely to engage at a given moment. Every channel (Email, Push, In-App, SMS, Live Content) is assigned a score from 0 to 100, with higher probabilities translating to a higher chance of a customer engaging, interacting, and taking action on a message.

Predictive Segmentation

Predictive Scores help you automate audience selection by identifying high-value customers for each of your marketing goals, as in those most likely to purchase, churn, engage with content, respond to an offer, renew a subscription, upgrade, and so on. Using AI and machine learning models, Blueshift’s Predictive Scores calculate each customer’s likelihood to perform a business goal or action. Each customer is assigned a score from 0 to 100, with higher probabilities translating to a higher chance of performing the desired goal.

Once computed, Predictive Scores are available throughout the Blueshift platform, including within the customer profile, segmentation, recommendations, campaigns, and templates. You can create highly targeted segments that focus on high or low propensity customers by defining which predictive score ranges to target in their campaigns. Similarly, predictive scores can be used in campaign journey building to move customers through different paths and receive different messages and offers based on their propensity to perform a certain action (i.e., purchase, subscribe, and so on).

You can export the predictive scores to any 3rd party application, paid media channel, or back to your internal systems for deeper analysis.

Additional information

Was this article helpful?
0 out of 0 found this helpful



Please sign in to leave a comment.