Blueshift commits to supporting the Open Data Initiative

Blueshift is excited to announce support for Open Data Initiative sponsored by Microsoft, Adobe & SAP. The Open Data Initiative ensures data flows efficiently within organizations, between relevant roles and systems to build a unified single customer view that powers all customer journeys. A Single Customer View builds the foundation that powers personalized customer journeys using AI and predictive analytics.

The Open Data Initiative is based on three guiding principles:

  • Control: Organizations own and maintains complete, direct control of all their data.
  • Intelligence: Customers can enable AI-driven business processes to derive insights and intelligence from unified behavioral and operational data.
  • Open: A broad partner ecosystem should be able to easily leverage an open and extensible data model to extend the solution.

Blueshift’s mission is to empower marketers with an AI-first customer data platform to power cross-channel marketing. Customer profiles within Blueshift are updated in real-time by unifying cross-channel identities and behaviors to personalize user journeys. Blueshift’s industry leading AI powered customer journey helps marketers:

  • Audience: Determine “who to target?” with predictive audience scoring
  • Content: Compute “what to say to each user?” with ML powered recommendations
  • Cadence: And control the right timing and channel for message delivery with “when and where to message?”

Blueshift is committed to build support for Experience Data Model (XDM), the common format to exchange customer information including CRM, behavior, transactional and more between systems. Blueshift is built on noSQL technology that adapts to customer specified data models and natively supports JSON formats. With support for the Open Data Initiative, Blueshift customers will be able to import CRM, behavior & transactional data from Microsoft Dynamics, Adobe Experience Cloud & SAP, while quickly enhancing user journeys in these systems with Blueshift’s Customer Data Platform computed predictive scores and 1:1 computed personalizations.

A.I. to reach your audience

Facebook Custom Audiences Just Got Smarter with Blueshift’s AI

In the rapidly evolving world of mobile devices, social media and the always-connected consumer, marketers want to get their messages out and amplify them quickly. Now more than ever, Lester Wunderman’s* principle of “communicating with each customer as an audience of one” takes on a new level of importance. And this means getting the right message, to the right person, at the right time on the right channel.

Facebook’s recent policy changes to prioritize content from friends over those from businesses puts even more pressure on us marketers because our content is going to be de-emphasized. This means we need to do more to get the same value from our ad impressions. And while Facebook has given us the basics of targeting in their Ad network with techniques like Custom Audiences, in today’s world, this is not enough.

Custom Audiences just got a little brighter

Custom Audiences is a targeting technique that enables you to upload a list of customers and prospects with their email addresses that Facebook then uses to find and serve your ads to them on its network of properties. Facebook can also use its data about a Custom Audience profile to find similar audiences. A nice feature that improves targeting and reach of episodic Ad campaigns of the “Wunderman” era but falls short in today’s fast changing environment. At Blueshift, we’ve taken this idea to the next level. We use our Artificial Intelligence (AI) techniques to enable you to create dynamic segments that we call Predictive Audiences and use them as Facebook Custom Audiences for your Ad campaigns on Facebook. You immediately benefit in three important ways:

  1. You get highly relevant Predictive Audience segments that are created using AI and machine learning techniques that evaluate hundreds of variables over large data sets to create highly targeted dynamic segments. You can now create ads that directly speak to these groups.
  2. Your Blueshift Predictive Audiences can be synced with your Facebook Custom Audiences in real-time ensuring that as people move through the buyer’s journey, your ads on Facebook remain relevant to the stage they are in. For example, a visitor to your site who has browsed your catalog should see different ads from a prospect that is yet to look at your catalog. But once the casual browser becomes more interested, your message should change accordingly.
  3. You can run similar multi-channel campaigns simultaneously across email, mobile, website and Facebook using the same Predictive Audience segments to drive engagement. This way you have a relevant message that reinforces your brand across channels

Facebook Custom Audiences Just Got Smarter with Blueshift’s AI. Using Blueshift's AI, brands can now optimize their RoI on Facebook, and drive 1:1 customer experiences. The latest release extends Blueshift's Cross-Channel Platform that already supports channels like Email, Mobile Push notifications, SMS and Websites.

With declining organic reach and increasing Ad prices, marketers need to keep innovating

As the Facebook network keeps growing and their policies shift towards favoring friends over organizations, business reach will continue to decline. And just as with property in Manhattan, San Francisco and Mumbai, when supply drops and demand increases, prices go up. This is clearly reflected in ad prices on Facebook. A recent study by Adstage reports that Facebook CPMs (cost of impressions) increased 171% and CPCs (cost per click) by 136% while CTRs (click through rates) remained unchanged in 2017.

Source: Adstage (

The only way for marketers to beat this trend is to out-think and out-execute the next guy. At Blueshift, we’re here to help you do both.

See Also
Activating Customer Data

Activating Customer Data with Graph Technology

Graph technology powered customer experience

What do Netflix, Amazon, LinkedIn, Facebook, and Google have in common? While they all serve different needs, they do that in a unique way by delivering an individualized experience to hundreds of millions of users at scale. From a user’s perspective, these brands seem to have an uncanny ability to have a 1:1 conversation, and understand each user’s unique tastes and preferences. In fact, no two users have the same experience with any of these brands. By delivering unique personalized experiences, they have gained incredibly loyal users that keep coming back for more and have become dominant in their respective categories.

But, what technological advantage do these companies have that gives them the ability to deliver individualized experiences at scale? If you look under the hood, unlike the previous generation of consumer companies that built customer experience on traditional IT systems, these leaders leverage a graph-based technology stack.

Before we continue, let me outline what we mean by a graph-based technology stack.

Let’s use Netflix as an illustration.

Behind the scenes, Netflix has built one of the largest graph of its users and their content preferences. Each time a user views, rates or adds a movie to a watch list, Netflix updates this graph with the user’s behavior in near real-time. Subsequently, Netflix uses this graph to deliver a rich user experience that recommends the next movie for a user to watch based on techniques such as what’s trending in user’s location, similar user preference, or a user’s affinity to a certain genre based on past behavior. Netflix delivers this experience to the user on all channels including apps, website and email. Every user engagement enriches the graph for all users. So the next time a user logs in, Netflix can further personalize the experience for the user, keep churn low and keep users coming back for more.


Personalized Netflix home page for a user


Netflix user movie taste graph captures user intents and interests.

Similar interaction and data graphs power the consumer experience of Facebook, Amazon, LinkedIn and Google. In the future we believe every digital company will have such an interaction graph. While the technology obstacles required to build, maintain and use such graphs are formidable, the existence of data underlying the graph is undeniable no matter which industry you are in.

Challenges in building an interaction graph

If data is readily available, then why are more brands not able to deliver an individualized and relevant user experience? Past efforts to build individualized experiences using an enterprise data warehouse have failed due to slow ETL processing, long query times and the disconnected nature of engagement channels that require sub-second response times for accurate decisioning. By the time user data is computed and activated, it is very likely stale and out of date, resulting in user annoyance instead of delight. Some forward thinking companies have recognized the flaws of a data warehouse driven approach, and embarked on building a user graph in-house using open-source graph databases.

Building such a graph in-house has several challenges that include:

  • Real-Time: It requires updates in real-time as users interact across website, mobile, email and other channels. The graph should support highly concurrent, low-latency writes, and high throughput search/queries.
  • Cross-Device: Users may not always be signed in and may be using multiple devices, which requires tracking plus merging anonymous and known behaviors across devices. The graph service needs to capture device identifiers, cookies, first party data and 3rd party data to enable deterministic and probabilistic profile tracking and merges.
  • Learning: The graph needs to be enriched with real-time user intents and long-term interests derived from behaviors. This requires algorithms suited for online learning and models that update in near real time with new data.
  • Scale: Depending on the size of the user base and content catalog, the graph may need to scale to processing billions of edges resulting in terabytes of data, while supporting sub-second query responses.
  • Data Fragmentation: On-going ETL and building connectors to deal with data fragmentation and evolving data schemas makes implementations brittle.
  • Resources: Budget and resourcing constraints to hire a team of engineers, analysts, data scientists and managers to build the technology stack and maintain integrations.

How we use graph technology at Blueshift

Blueshift’s next generation customer data platform is powered by an interaction graph: A real-time undirected graph created using 1st party behavior data from every engagement touch-point. Blueshift’s customer data platform captures all your user interactions in real-time and is available across every channel. Blueshift’s Interaction Graph powered CDP is usable out of the box, and companies can onboard terabytes of data in just few days.

Leading digital brands such as LendingTree, BBC, IAC and Udacity are using Blueshift’s Interaction Graph powered CDP to engage their consumers with a unique individualized customer experience across every touch point and seeing a significant lift.

Ready to learn more about Blueshift’s Customer Interaction Graph, contact us today.

In a follow up to this post, we’ll talk about the algorithms and systems required to build the interaction graph, stay tuned.

Real-Time Segment

Behind-the-Scenes: Real-time segments with Blueshift

(Here is a behind the scenes look at the segmentation engine that powers Programmatic CRM.)

Real-time segmentation matters: Customers expect messages based on their most recent activity. Customers do not want reminders for products they may have already purchased or messages based on transient past behaviors that are no longer relevant.

However, real-time segmentation is hard: it requires processing large amounts of behavioral data quickly. This requires a technology stack that can:

  • Process event & user attributes immediately, as they occur on your website or mobile apps
  • Track 360-degree customer profiles and deal with data fragmentation challenges
  • Scale underlying data stores to process billions of customer actions and support high write and read throughput.
  • Avoid time consuming steps of data modeling that require human curation and slows down on-boarding

Marketers use Blueshift to reach each customer as a segment-of-one, and deliver highly personalized messages across every marketing channel using Blueshift’s Programmatic CRM capabilities. Unlike previous generation CRM platforms, Segments in Blueshift are always fresh and updated in real-time, enabling marketers to respond to the perpetually connected customer in a timely manner. Marketers use the intuitive and easy to use segmentation builder to define their own custom segments by mixing and matching filters across numerous dimensions including: event behavioral data, demographic attributes, predictive scores, lifetime aggregates, catalog interactions, CRM attributes, channel engagement metrics among others.


Segments support complex filter conditions across numerous dimensions

Segments support complex filter conditions across numerous dimensions

Behind the scenes, Blueshift builds a continually changing graph of users and items in the catalog. The edges in the graph come from user’s behavior (or implied behavior), we call this the “Interaction graph”. The “interaction graph” is further enriched by machine-learning models that add predicted edges and scores to the graph (if you liked item X, you may also like item Y) and also expand user attributes through 3rd party data sources (example: given the firstname “John”, with reasonable confidence we can infer gender is male).

Blueshift interaction graph

Blueshift interaction graph

The segment service can run complex queries against the “interaction graph” like: “Female users that viewed ‘Handbags’ over $500 in last 90 days, with lifetime purchases over $1,000 and not using mobile apps recently and having a high churn probability” and return those users within a few seconds to a couple of minutes.

360-degree user profiles

For every user on your site/mobile app, Blueshift creates a user profile that tracks anonymous user behavior and merges it with their logged-in activities across devices. These rich user profiles combine CRM data, aggregate lifetime statistics, catalog-related activity, predictive attributes, campaign & channel activity and website / mobile app activity. The unified user profiles form the basis for segmentation. A segment query matches these 360 degree user profiles against the segment definition to identify the target set of users.

360-degree user profiles

360-degree user profiles in Blueshift

Multiple data stores (no one store to rule them all)
The segmentation engine is powered by several different data stores. A given user action or attribute that hits the event API is replicated across these data stores including: timeseries stores for events, relational database for metadata, in-memory stores for aggregated data & counters, key-value stores for user lookups, as well as a reverse index to search across any event or user attributes quickly. The segmentation engine is tuned for fast retrieval of complex segment definitions compared to a general purpose SQL-style database where joins across tables could take hours to return results. The segmentation engine leverages data across all these data stores to pull the right set of target users that match the segment definition.

Real-time event processing

Website & mobile apps send data to Blueshift’s event APIs via SDKs and tag managers. The events are received by API end-points and written to in-memory queues. The event queues are processed continuously in-order, and updates are made across multiple data stores (as described above). The user profiles and event attributes are updated continuously with respect to the incoming event stream. Campaigns pull the audience data just-in-time for messaging, which result in segments that are continuously updated and always fresh. Marketers do not have to worry about out of date segment definitions and avoid the “list pull hell” with data-warehouse style segmentation.

Dynamic attribute binding

The segmentation engine further simplifies onboarding user or event attributes by removing the need to model (or declare) attribute types ahead of time. The segmentation engine dynamically assesses the type of each new attribute based on sample usage in real-time. For instance, an attribute called “loyalty_points” with a value of “450”, would be interpreted as a number (and show related numeric operators for segmentation), while an attribute like “membership_level” with a value of “gold” would be dynamically interpreted as a string (and show related string comparison operators for segmentation), or an attribute like “redemption_at” with a value like “2016-09-23” will be interpreted as a timestamp (and show relative time operators).

Several Blueshift customers have thousands of CRM & event attributes, and are able to use these attributes without any data modeling or declaring their data upfront, saving them numerous days of implementing data schemas in SQL-based implementations.

The combination of 360-degree user profiles, real-time event processing, multiple specialized data stores and dynamic attribute binding, empowers marketers to create always fresh and continuously updated segments.