Exploring Opportunity Marketplace Sections and Recommended Logic

Opportunity Marketplace’s main sections offer recommended opportunities using specific recommendation logic.

Assignments created within Opportunity Marketplace are displayed in this section, including:

• Projects
• Fellowships
• Vocational Training
• Internships

The data comes from the Assignments feature within OMP, and the assignments are recommended based on a calculated matching score. The score reflects how well the user's skills and preferences align with the assignment's requirements, whether the assignment's location is compatible with the user's location, and whether the assignment's job role matches the user's target roles. Assignments with higher scores are ranked and recommended first.

The final score is calculated using the following formula: ((Total Attribute Points + Target Role Points) / (Number of Required Attributes + 1)) * 0.8 + (Location Match Score * 0.2). Only assignments with a score above 0 are recommended.

The skills/attributes score considers the following factors:

• Skill match: A skill from the assignment counts as matched if the user has the same skill. This contributes 0.25 to the score.
• Critical/core skill match: A skill from the assignment is marked as critical or core. This contributes an additional 0.25 to the score, even if it does not match any skill of the current user.
• Passionate skill match: A skill from the assignment is marked by the user as passionate. This contributes an additional 0.25 to the score.
• Proficiency level match: When the user's proficiency rating is equal to or higher than the requirement of the assignment, this contributes an additional 0.25 to the score.
• Each skill can contribute up to 1.0, depending on the combination of factors.

The target role score is determined using binary logic:

• If any of the employee's target roles match the assignment's job role, the target role score is 1.
• If none of the employee's target roles match the assignment's job role, the target role score is 0.

The location score is determined by the assignment’s work mode and location match:

• When the assignment is remote or hybrid (remote and on-site), it is treated as location-compatible and scores 1.
• When the assignment is on-site, a location match with the user is required to get the location score of 1.
• When the work mode of the assignment is not defined and the location is not defined, the location score is 1.
• When the work mode of the assignment is not defined but it has a location that matches the user's location, the location score is 1.

Users can select an assignment to review and apply, bookmark assignments that are relevant, or select Not Interested to remove it from the results.

Each section within OMP has an Explore More link. Explore More shows all of the opportunities for that section, with a filter that can be used to narrow down the opportunities listed on the screen. The filters provided differ by section and the opportunities available within that section.

Some sections provide a list of attributes to be used as a filter. Selecting one or more attribute(s) will show only the opportunities for that attribute. Attributes and ratings can be edited using the View All in Growth Portfolio link.

Internal open job postings, from the SAP SuccessFactors Recruiting module, are listed in this section. They’re recommended by matching the following criteria, listed in descending order of priority:

• For customers using Growth Portfolio, the opportunity, from the pool of the latest 1000 open jobs, that best matches the user's skills and attributes from their Growth Portfolio is prioritized.
• The opportunity's title matches the user's target role.
• The opportunity's title matches the user's job code name.
• The opportunity's job code matches the user's job code.
• For non-EC instances, the equivalent field of job code defined in the user data model is used for the second and third criteria.

This section displays two types of mentoring opportunities from the SAP SuccessFactors Mentoring module:

• Mentors
• Mentoring Programs

Users see recommended mentors that match their preferences from one or multiple mentoring programs that they joined. If they haven't joined any mentoring program, they only get recommended mentoring programs.

Opportunities are listed from all three types of mentoring programs: open enrollment, supervised, and unsupervised programs.

Users can find the learning items recommended specifically for them in the Learn New Skills section. Learning items associated with a greater number of the user's skills are prioritized. Learning items with a lower level than the user’s current skill level are excluded. Five types of learning opportunities are displayed in this section:

• Course
• Curriculum
• Program
• Collection
• QuickGuide

In this section, users can discover three different recommendation types for learning content:

• Admin Recommendations: These items are recommended through Assignment Profiles and identified by the label of Recommended by Learning Team.
• Peer Recommendations: These items are recommended by peers and identified by the label that indicates who recommend it.
• Personalized Recommendations: These items are recommended based on the employee's skills and attributes.

In addition to the Learn New Skills section in Opportunity Marketplace, learning recommendations based on an employee's skills and attributes are also available in the Opportunities to Grow sections in Growth Portfolio and the latest Career Worksheet.

In this section, job roles that best match users and can be added as target roles are displayed. Either Suggested Roles or Career Explorer are used to recommend roles to the user.

The Suggested Roles feature provides a proactive step in employee development by automatically recommending future roles to an employee. Manage Suggested Roles in Admin Center is used to configure these suggested roles, which are used in the Career Worksheet, Growth Portfolio, and Opportunity Marketplace.

The Suggested Roles option uses an algorithm based on proximity of role in Career Path, Competencies associated with the role, common job family, open positions for the role, and popularity of the role within the team. With the latest Career Worksheet, in addition to the Suggested Roles recommendation algorithm, the role recommendation logic considers the skills and attributes that are tagged as Core or Critical or marked as passionate in Growth Portfolio. Additional details about Manage Suggested Roles are available in the Enabling Career Worksheets unit.

The Career Explorer option is powered by machine learning technology, and job role recommendations are generated by applying machine learning to user data that includes user attributes and data related to users' job history. The data is synchronized periodically from SAP SuccessFactors to the recommendation engine on SAP AI Business Services, and job role recommendations are based on Background Information, Employment Information, and Competency ratings.

Career Explorer can only be used when Employee Central, Succession & Development, and Job Profile Builder are enabled, and there are at least 1,000 employee job change records (identified by job code changes) in the system.

With Intelligent Recommendations users can get personalized recommendations powered by SAP AI Business Services. This system gathers individual data from Opportunity Marketplace Assignments, SAP SuccessFactors Recruiting, and SAP SuccessFactors Learning to analyze and identify patterns. Machine learning algorithms are then applied to generate personalized opportunity recommendations. This is displayed in the Top Picks for You, Ignite Your Role, and Reach Your Aspirations sections.

The following data sources are used to generate Intelligent Recommendations:

• User Profile Data: Job Location, Job Code, Departments, Division.
• Growth Portfolio Data: Attributes that users are interested in, attributes with a Critical tag, Attributes ID.
• Assignment Data: Attachment Type, Attributes ID.
• Recruiting Data: Job Title, Job Location, Job Posting related Growth Portfolio attributes, Applied Jobs.
• User Activity Data in OMP: Bookmarks of assignment and learning opportunities, Opportunity applications.

Top Picks for You

Machine learning technology recommends opportunities based on a user's profile and activity data. Intelligent recommendations are boosted for each user by adopting the following strategy in the dimension of skills and attributes:

• Assignments and open jobs are more weighted, when their required skills/attributes are marked by the user as being passionate about or being tagged as critical.
• Only learning items that help you improve the proficiency level of your skills are recommended.

Ignite Your Role

Intelligent opportunity recommendations in this section focus on improving the skills that users already have and are needed in a user's current role. The following attributes are considered to filter or boost the intelligent recommendations:

• Skills/attributes that the user already has.
• Skills/attributes that are needed for the user's current job role.
• Only learning items that help you improve the proficiency level of your skills are recommended.

Reach Your Aspirations

Intelligent opportunity recommendations in this section focus on the user's aspirations. The following attributes are considered to filter or boost the intelligent recommendations:

• Skills/attributes in which the user is interested.
• Skills/attributes that are required for the user's target role.
• Skills/attributes that are required for the user's development goals.
• Only learning items that help you improve the proficiency level of your skills are recommended.

Cards for learning, open job, and assignment recommendations from Opportunity Marketplace are featured at the top of the latest home page. Selecting a card will open the detail page for that opportunity.

New recommendations appear as cards on the latest home page according to the following rules:

• If intelligent opportunity recommendation is enabled, you see these cards when there are new recommendations for learning, open jobs, or assignments.
• If intelligent opportunity recommendation is not enabled, you see these cards when there are new recommendations for learning, open jobs, or assignments, and you haven't visited Opportunity Marketplace for at least two weeks.
• You see only one card for each opportunity type at a time. The system displays the most recent opportunity of each type.
• Each card stays visible for 30 days unless a newer recommendation replaces it within that period.

The Manage Opportunity Marketplace tool in Admin Center allows administrators to enable the types of opportunities that can be recommended, which sections to show, and the order of the sections.

Additional settings are available for specific sections:

Explore Career Options: Select from the Suggested Roles default or change to Career Explorer for recommendations.

Open Jobs: Pay grade-based and geographic filters can be added to control which open job opportunities are recommended to employees.

• For job level filters, administrators can select a Pay Grade from the list below, or upload filter rules in a CSV file to match user's pay grade with a custom job level field.
  • Same pay level and all higher levels. This is the default setting.
  • Same pay level and up to one level higher.
  • Same pay level and up to two levels higher.
• For the geographic filter, administrators can configure the filters to recommend only open jobs that match the user's country/region or location.

• Opportunity Marketplace offers personalized recommendations for assignments, jobs, mentoring, and learning based on user skills and preferences.
• Users can explore opportunities through sections like Broaden Your Experience, Discover Open Jobs, and Connect with People.
• Intelligent Recommendations use machine learning to suggest opportunities aligned with user profiles, skills, and aspirations.
• Admins can manage opportunity types, section visibility, and recommendation settings in the Manage Opportunity Marketplace tool.
• Explore Career Options provides role recommendations using Suggested Roles or Career Explorer, leveraging user data and machine learning.