Blueshift: Personalization & Decisioning

Blueshift's response to Questions on Personalization & Decisioning in the RFP Guide

Overview: Blueshift enables you to use every form of data (events, user attributes, catalog) as dynamic variables in emails, mobile push notifications and live content for websites and apps. Blueshift's support for the widely used Liquid template language helps marketers build complex filters conditions easily.

Blueshift's Recommendation Studio, built with patent pending Artificial Intelligence technology, is the most flexible and transparent system for building recommendations that can be used by non-technical marketers. Blueshift automatically computes various forms of recommendations: based on events (re-targeting), collaborative filtering, affinity based, trending items, catalog change based etc. These recommendation types can be sorted, filtered and combined in different ways to suit your business needs. Recommendations can be configured from a visual studio that offers previews for different users, and once configured, can be attached to any email, web or mobile template with 1 click.

Blueshift's Responses to Questions on Personalization & Decisioning

Personalization

1. Describe how your solution creates dynamic content. What user and event attributes can be used to personalize content?

Marketers can use Liquid template language to define business rules and personalization within any message template, including email, SMS, push, in-app, or other channels via Cloud App template based on any user data attributes and preferences. As an example, marketers may want to have logic in the message template to check if the customer’s gender is known, and then display a different type of message or content based on the gender. Similarly, using Liquid template language, marketers can easily include dynamic content based on country, geographic region, user's language (i.e., English, French, Spanish, etc.), user's type (i.e., new vs existing or free vs paid), and other attributes. In addition to being able to personalize the message content, message text and subject lines can also be customized based on any user data attributes.

Our message editor allows the marketer to easily access any user data attribute via Liquid template language. More specifically, marketers can simply start typing in the liquid variable syntax, {{user}} and will automatically see a list of user data attributes that are available for personalization variables.

Additional information on how to add personalization and dynamic content in your templates

Additionally, Blueshift provides an intuitive and easy way to apply personalized dynamic content and product recommendations on the website via our Live Content capability. It works the same way as you would personalize content in the channels as described above. Within the Live Content template, you can easily personalize the web personalization content (i.e., title/headline) based on any user data attributes. Furthermore, you can control what content is shown based on any user data attributes by creating an audience segment with the user data attributes and assigning that audience segment to a Live Content campaign. As an example, you may want to show different content based on the user's lifetime value (LTV). For users with a LTV > $500, you can setup a Live Content campaign that shows a Free Shipping offer, whereas for users with a LTV < $500, you can setup a different Live Content campaign that shows a 15% discount along with Free Shipping offer to provide additional incentive to purchase.

Additional information on our Live Content capability


2. Can your solution fetch external content in real-time from in-house personalization systems and include them in messages right before send?

Yes, Blueshift provides the ability to retrieve external content from any system in real-time and populate it into a message/communication right before message send using our external fetch API.

Additional information on external fetch


3. Does your solution autonomously update the text, images, offers, and other template elements in real-time for each user based on the latest user data and behaviors?

Yes, Blueshift platform autonomously learns about users by taking into account a their whole histories with the brand that encompasses historical data, behaviors, and transactions as well as the latest user profile data and interaction/behavioral data. It then applies our patented AI technology on top of this data to enable real-time decisioning and trigger the next-best-action for each individual user based on that deep user understanding. More specifically, Blueshift's real-time decisioning capabilities include the following:

• personalization/recommendations (next-best-offers)
• category affinities (category affinity, brand affinity, product attribute affinity)
• predictive scores (predicting user's likelihood to perform a specific action, such as purchase, churn, retention, engagement)
• channel optimization (next-best-channel)
• engage time optimization (next-best-time)

As users' interactions and behaviors happen in real-time, this data is automatically ingested into the Blueshift platform and immediately impacts the real-time decisioning engine to influence what the next best action/message will be for a given user. Most importantly, marketers can easily take action on these real-time decisioning capabilities and use them as levers to make smarter decisions and orchestrate intelligent, automated user journeys that are fully customized and personalized such that the right message is sent in the right channel at the most optimal time for every individual user.

Additional information on our channel optimization
Additional information on our engage time optimization
Additional information on our recommendation studio
Additional information on segmentation based on category affinity
Additional information on predictive scores


4. For which channels do you support dynamic content personalization?

Blueshift supports dynamic content personalization within any message template, including email, SMS, push, in-app, website, or other channels via Cloud App template based on any user data attributes and preferences. In addition to being able to personalize the message content, message text and subject lines can also be customized based on any user data attributes.


Decisioning

5. Can your solution optimize message content, timing, and channel at the user-level based on real-time data in the customer profile, predictive scoring values, and customer behaviors?

Yes, Blueshift autonomously learns about users by taking into account their whole histories with the brand that encompasses historical data, behaviors, and transactions as well as the latest user profile data and interaction/behavioral data. It then applies our patented AI technology on top of this data to enable real-time decisioning and trigger the next-best-action for each individual user based on that deep user understanding. Marketers can then easily take action on these real-time decisioning capabilities and use them as levers to make smarter decisions and orchestrate intelligent, automated user journeys that are fully customized and personalized such that the right message is sent in the right channel at the most optimal time for every individual user.


6. Can your solution trigger a message in one channel based on a real-time interaction in another channel?

Yes, Blueshift offers advanced capabilities to trigger messages across multiple channels, including email, mobile push, in-app, SMS, onsite, 3rd-party applications, and paid media channels. With Blueshift, marketers can automatically trigger contextually relevant, timely messages in any channel in response to customers’ behaviors in another channel (i.e. an onsite transaction can trigger an order confirmation email and SMS). This lets marketers immediately reach customers at key moments across relevant channels so they can drive conversion, influence actions with timely notifications, re-engage customers during critical win-back periods, and drive upsell.

More specifically, our platform uses a combination of user metadata, transactions, browsing behaviors, and catalog/content changes to trigger messages based on the set criteria as soon as a desired event occurs. Marketers then have the ability to define the event (i.e. sign up, add to cart, etc.) that triggers the campaign, the sequence of messages that will be triggered, the content included, which channels the messages will be delivered on, and any other parameter needed. Event-triggered campaigns can then be built using Blueshift's visual campaign builder and can include multiple stages, multiple branchings that span across multiple channels to provide a consistent, personalized omnichannel user experience.

Additional information on event triggers as well as other types of campaigns


7. Can your solution optimize message send times at the user and geographic levels?

Yes, Blueshift supports send time optimization based on user and geographic levels. In addition, marketers can leverage the platform's intelligent optimization features like day-parting, predictive engage time optimization (based on when users are most likely to engage), and other data points of user engagement. Messages can be sent using the predictive affinity hours, as well as sent at a customizable time as indicated by your user’s time preference. Unlike other vendors that only support this for the email channel, this engage time optimization feature is available across multiple channels, including email, SMS, website, and mobile push.


Recommendations

8. Does your solution have a visual interface in which marketers can create and manage recommendation types without technical knowledge? Is this a native capability or through a partnership/ additional integration?

Yes, Blueshift has a native/out-of-the-box recommendation studio that provides marketers with an intuitive, easy-to-use drop-down interface to build recommendation schemas that pull directly from your catalog in a self-service manner, without the need for IT teams or data scientists. Marketers can create content blocks with product recommendations, recommended offers, or other brand content like blogs or videos that adapt and dynamically personalize to every individual user in real-time based on their current context, recent activity, and their product, category, or brand interests.

Additional information on our Recommendation Studio


9. Describe what types of recommendations your solution supports (i.e. collaborative filtering, trending items, similar items, new items, expiring items, etc).

Within Blueshift’s recommendation studio, marketers can define recommendation schemes for everything from abandoned content, related items, top trending items, top sellers, most viewed, “users also bought,” next-best-product, expiring items, recent additions, and more. For recommending relevant, contextual predictive content/items/products, we use matrix factorization and collaborative filtering algorithms.

Marketers also have advanced controls to define what kinds of content to include or exclude within each content scheme, mix and match recommendation types, and set how to backfill recommendations to ensure that users receive the most relevant and highest converting offers and messages.

Marketers can also leverage Interest Alerts to instantly notify users with content based on their topics of interest.

Additional information on recommendation types


10. Does your solution ingest product, content, and offer catalog data and use dimensions of that data (i.e. product name, price, etc.) within dynamic recommendations?

Yes, Blueshift easily ingests your content and product catalogs (i.e., products, blog articles, videos, offers, etc.) in a very flexible way and leverage all the metadata fields from your catalogs. Our customers typically have dynamic catalogs, where the pricing, inventory, image, etc., are constantly changing. We provide the ability to refresh the catalog based on a scheduled cadence by setting up automated catalog import jobs that runs hourly/daily/weekly. For scenarios where real-time update is needed, we also provide a Catalog API that can be used to dynamically update the content and product attributes (i.e, price, availability, etc.) immediately. Many of our customers have large and extensive catalogs, where millions of products are constantly changing over time, and our platform has been architected to scale and accommodate any catalog size to meet your current and future needs as your content and product library continue to grow and evolve over time.

Using our built-in recommendation engine, Blueshift can then easily recommend the most relevant next-best items (i.e., offers, content, products, etc.) from the catalogs based on the catalog metadata and user data and behaviors and serve that content dynamically within user communications across channels.

Additional information on our catalog capabilities and how to ingest your content catalog

Additional information on our Catalog API


11. Does your solution allow us to import recommendations from our in-house team? If yes, describe how.

Yes. Blueshift supports customers importing recommendations from their in-house team by providing the ability to easily upload their recommendations directly into Blueshift as recommendation feeds. Our customers that have a data science team and have their own recommendations typically will combine their external recommendations with our AI-powered recommendations that are built using our recommendation studio and then test, experiment, and optimize the best performing combination of recommendations that result in the highest engagement and conversions in their marketing messages.

Additional information on how to import your own external recommendations and how to use it in our recommendation studio


12. Does your solution support combining multiple types of recommendations within a template? If yes, describe how.

Yes, within Blueshift’s recommendation studio, marketers have advanced controls to define what kinds of recommendations to include or exclude within each recommendation scheme, mix and match recommendation types, and set how to backfill recommendations to ensure that users receive the most relevant and highest converting offers and messages. Using Blueshift’s recommendation studio, marketers can create multiple content blocks with product recommendations, special offers, or other brand content like blogs or videos to a message template that adapt and dynamically personalize to every individual customer in real-time based on their current context, product/brand affinities, and predictive scores. Multiple recommendation types can then be incorporated into a single message template.

Additional information on recommendation types


13. Does your solution generate unique recommendations for every user based on real-time data? Does it offer the ability to preview recommendations for different users and add filters?

Yes, once recommendations are used within a message template and the campaign is running, recommendations presented to each user update in real-time to each user based on their current context, affinities, recent activity and behaviors, and the latest catalog data. This ensures that the content remains current and relevant and avoids fatiguing users. Blueshift allows marketers to set up message templates that incorporate recommendations once and be confident that the content delivered is always relevant even as users' interests and intentions evolve over time. Additional information on our recommendation studio

Marketers can also preview what recommendations look like for any given user or users within a segment within the message editor. Additional information on previewing recommendations within our email editor