A - F

In Marketing Cloud Personalization, an account represents a company or organization that has individuals who engage with your company. For example, you could have individual users who visit your site who all work for ABC Company. If you have accounts enabled on your dataset, you can see analytics by account, activate (personalize) based on account, and view account profile data.

For business-to-business (B2B) clients, a profile built both at the individual prospect and customer level, and for the account to which these clients belong. For example, Marketing Cloud Personalization can have:

• An account profile of ABC Company
• Individual profiles for anonymous visitors from ABC Company
• Named profiles for Bob and Alice from ABC Company

Using the data collected and stored within Marketing Cloud Personalization to affect a customer experience in some way. Activation is also known as personalization because it’s the act of using information known about a person to deliver a personally relevant experience.

This reporting term gives an overview of campaign and goal statistics, including trends for impressions, goal completions, and click-throughs. Use the activity reporting section in Marketing Cloud Personalization to analyze information about recent visitors, see actions taken by visitors and customers, group users by cohorts, and see other data.

Includes information on pages visited, number and frequency of visits, and page-level engagement based on mouse movement, scrolling, inactivity, and time spent.

In the recommendations system, the reference point that an ingredient or exclusion uses as the basis for determining which items to return. For example, to use a Co-Browse ingredient, set the anchor item. Marketing Cloud Personalization returns items for what’s being viewed on the page, in the visitor's cart, last purchased, or purchased by the visitor within a specific number of days.

Data that is unique to a user or account. Attribute data is collected from various sources, including:

• contact forms
• survey responses on your site
• external databases such as a CRM, email marketing solution, marketing automation tools, or a data warehouse

Type of attribution. One of the following:

Type	Description
View	Shows whether visitors saw the campaign and converted during the selected attribution window.
Click	Shows whether visitors clicked the button or link in the campaign and converted. Applies only to campaigns that include a button or a link.

The period between the visit impression and the goal completion of a campaign. Marketing Cloud Personalization offers four attribution windows: 30 minutes (default), 1 hour, 24 hours, and 1 week. Because some products have a longer consideration cycle, review how long the timeline to conversion is, and then use that time frame when reviewing data.

Specific individuals, groups of individuals (such as segments), or accounts (such as companies) that are targeted by personalization campaigns, or who view them.

Total revenue collected divided by the number of orders. AOV quantifies the average basket size of the visitors who saw the campaign and made a purchase during the attribution window.

The Marketing Cloud Personalization JavaScript beacon places a first party cookie on the visitor's browser. The beacon sends data for that visitor back to Marketing Cloud Personalization. Data includes pages visited, links clicked, time on site, number of visits, geolocation, and referral source, as well as other collected custom data. The beacon is integrated in either of two ways:

Approach	Description
Synchronous	Loads the beacon before the page loads. Synchronous integration allows Marketing Cloud Personalization to prevent page flicker, a momentary flash of the original page content.
Asynchronous	Loads the beacon after the page has loaded. With asynchronous integration, Marketing Cloud Personalization can’t protect against flicker.

Shows information about visits to your site. You can graph out the number of visits based on new versus returning visitors, engagement level, logged-in status, and purchase behaviors. You can apply one filter to adjust the results and make comparisons.

You can use boosters to tailor your recommendation recipe to the 1:1 level. When you use a booster, the visitor's affinity score is considered, and items that match that affinity are boosted in the recommendations query results. In other words, if you boosted the brand affinity in your recipe, visitors who show a preference for a particular brand see items with that brand first.

Systems that companies use to engage with customers over the phone (for example, a toll-free number). Using an integration, Marketing Cloud Personalization can pass data including personalized messages and recommendations to these systems to help representatives best serve customers.

Contains experiences and messages designed to personalize the interaction a visitor has with your channels (Web campaigns excepted).

Created for campaigns only. Associated with a specific set of narrow actions. Use campaign-level goals to avoid exposing visitors to the campaign after they’ve reached the goal. Visitors who reach the goal don’t see the campaign again. An example of an effective campaign goal is moving people through different audience segments. For example, after a visitor watches a getting started video, they would have completed the campaign goal of “Watched Intro Video” and wouldn’t see the message again.

Not applicable to Web campaign and experience rules. Rules set at the campaign level holistically control how the campaign renders. Rules can be based on particular factors, including:

• visitor or recipient segments
• location
• device type
• time of day
• visitor or recipient behaviors
• company
• industry

A campaign can be in one of the following states:

State	Description
Disabled	Set automatically when you create a campaign. A campaign in the disabled state isn’t “live” on your site.
Testing	To verify a campaign before publishing, change its state to Testing.
Published	When you’re ready to make your campaign live on your site or in your application, change its state to Published.

Collection of products and content, as well as related categories, and tags (such as brand, gender, style, keyword, and author). Marketing Cloud Personalization dynamically populates the catalog in real time with product and content data automatically extracted from the site. You can provide this information through a data feed, but gathering your data directly from your site means that your product and content information is always up to date.

The process of integrating a site with the Marketing Cloud Personalization catalog. After the catalog is mapped and Einstein Recipes are implemented, items from the catalog can be recommended to visitors.

A touch point used to interact with, and communicate with, visitors and customers. Depending on your Marketing Cloud Personalization license, you can access to channels for Web, email, and mobile channels, as well as third-party channels (integrations with other systems).

Occurs when a visitor clicks a button or a link being tracked by Marketing Cloud Personalization. A click can be a specific action you want to track, or it can be a button or a link driving visitors to another domain not tracked by Marketing Cloud Personalization. Example: A Login button that takes visitors to an application from a marketing site.

The total number of clickthrough events that occurred in the campaign. Clickthrough events are tracked only when a campaign has something to click, such as a button or a link.

The number of clicks divided by the number of impressions. If clickthrough events are zero, the clickthrough rate is also zero.

A business that uses Marketing Cloud Personalization services.

The algorithm that analyzes:

• items or content commonly viewed by previous visitors, along with
• the same item or content a visitor is viewing, or has placed in their cart

If a visitor is viewing an article, this ingredient returns articles that other visitors commonly viewed during the same browsing session in which they viewed that particular article.

An algorithm that analyzes

• items or content also purchased or downloaded by previous visitors, along with:
• the same item the visitor is viewing or has placed in their cart during the lookback period

For example, if a visitor placed a jacket in their cart, this ingredient returns items that other visitors have commonly bought with that jacket in the past 30 days.

Often referred to as the "people like me" algorithm, collaborative filtering is based on the alternating least squares (ALS) method of matrix factorization. This ingredient learns visitor intent through browsing and purchasing behaviors to best match their affinity categories. The ingredient then clusters the visitor with other visitors that have similar affinities. The results returned are based on the cluster as a whole.

A selection in Campaign Statistics used to compare campaign experiences against each other or against a control. If experience A is the baseline, then the revenue or conversion rate can be higher for experience B as compared to experience A.

In Campaign Statistics for an A/B tested campaign, the probability that the click-through rate for the updated campaign experience will exceed the click-through rate of the original version (control). For example, if confidence is 95%, the chance of making an error—deciding that the updated experience gets a higher click-through rate when it doesn’t—is 5%.

An area of a site that a developer has configured in the sitemap to make eligible for personalization. Examples: a homepage hero (personalized offers or recommendation) or product detail page (PDP) product recommendations row (similar items on the PDP).

Data that is passed to Marketing Cloud Personalization when a visitor lands on a site. Includes:

• the visitor’s IP address and referring source
• other information, such as geographical data and device type

Also referred to as implied data.

The total number of orders or goal completions collected divided by the number of unique visitors who saw the campaign.

In Marketing Cloud Personalization, a collection of events, catalog configurations, and user profiles. Datasets keep Marketing Cloud Personalization data separate and organized. An account can have multiple datasets. Data is partitioned so that data sent to one dataset is kept separate from data in other datasets. Partitioned data helps clarify distinct differences in customer engagement.

Defines the length of time a product or piece of content remains marked as new.

Provides a picture of each visitor’s true interests and intent based on what’s known about that visitor, including:

Data	Description
situational data	Examples: a visitor's referring site, email or ad campaign source, IP address, geo-location, device type, and operating system.
attribute data	Collected from contact forms and survey responses on your site, or from external databases such as a CRM, email marketing solution, or a data warehouse.
activity data	Examples: pages visited, number and frequency of visits, and page-level of engagement based on mouse movement, scrolling, inactivity, and time spent.
contextual data	Context of each page, such as category, brand, style, and keywords.

The number of times a message was dismissed using the close icon.

The number of dismissals divided by the number of impressions.

A message-level rule that limits the number of times to display a message:

• a specific interval
• all-time
• during a visitor's current visit

Feature that determines which factors to train in the machine learning models responsible for serving up recommendations. After it’s configured, Einstein Decisions analyzes these factors for each visitor to determine which promotions to show based on which are expected to generate the most lift.

Recommendation strategy in Marketing Cloud Personalization. You build recipes by adding one or more ingredients—or the core algorithms driving the recipe—as well as exclusions, and boosters. You can create a variety of combinations to serve up the right content or products based on an individual visitor’s behavior and affinities on your site.

An option in the Path report. The Path report shows the number of actions recorded for the page you selected in the dropdown, the bounce rate for this page, and the path for that page.

Any interaction a visitor has with a site, such as a click, a page load, or a message view (which is an impression).

Designates whether to show items in a recommendation. Usage examples:

• Tailor a recipe to avoid recommending products that are in the cart.
• Include items in the same category as what each visitor is viewing.

Use experiences to create different personalization results within the same campaign. For example, suppose you want to create a campaign for first-time visitors to your site. You want to show different message to visitors from Boston and San Francisco because you have events coming up in those two cities. To implement this approach, create three experiences in the same campaign:

• Boston visitors
• San Francisco visitors
• visitors from everywhere else

Use experience-level rules to control the visibility of these experiences

Data that a visitor provides intentionally, such as survey responses, purchase history, content downloads, or clicks.

Used with segments or global goals. Apply filters to the data shown in campaign statistics and some reports. When you apply a filter, only the people who meet the filter condition are included in the metrics. For example, you can compare how first-time and repeat visitors performed for a campaign, so you can cater experiences to each group. Or, you can see if your campaign is performing well on all devices, or only on mobile, or only on desktops. In addition to any filters you configure for your dataset, there are a number of pre-existing – or default – filters available for reporting and campaign statistics.