The recommendation engine uses context signals from the platform to personalize suggestions. This information is not publicly exposed and is handled according to the platform’s privacy rules. The system’s goal is to expand discovery, progression, and access to new opportunities.
What the engine does
That’s Me’s recommendation engine was designed to answer a simple yet valuable question: what is the most fitting next step for this person, based on what they’ve already achieved? In practice, this allows the platform to:- recommend upcoming events, courses, competitions, and experiences
- identify continuity between achievements already earned and new opportunities
- expand discovery of relevant paths without relying solely on manual search
- increase recurrence and re-engagement for issuers
- turn the achievement history into a living progression asset
How the intelligence operates
The engine combines different layers of context to produce more fitting recommendations.Intelligent event reading
When an event is created, the platform interprets its data to understand what it represents in terms of theme, category, level, format, modality, location, and skills involved.This reading creates a semantic foundation that allows events to be connected to one another, continuity to be identified, and the distribution of relevant opportunities within the network to be expanded.
Achievement history reading
From accepted achievements, the platform consolidates signals about a person’s trajectory: areas of greatest activity, progression patterns, recurring contexts, and possible development directions.The system does not publish grades, personal rankings, or value judgments. These inferences exist solely to improve the quality of recommendations.
Opportunity ranking
To rank recommendations, the engine considers factors such as alignment with the user’s goals, trajectory continuity, event context, format, location, timing, and interest signals.The result is a personalized list of opportunities most aligned with the person’s profile and current stage of development.
What makes this engine valuable
Most platforms end the experience at the record. That’s Me uses the record as a starting point. When an achievement enters the platform, it doesn’t just serve to prove something that already happened. It also starts informing what could happen next. This changes the role of the certificate:- it stops being just memory
- it becomes context as well
- it stops being just proof
- it becomes direction as well
- it stops being just a file
- it becomes distribution as well
Progression with coherence
One of the engine’s core principles is respecting the real progression of a trajectory. The platform prioritizes next steps that are compatible with the history the person has already demonstrated, avoiding artificial leaps and reducing noise in recommendations.- Example: Running
- Example: Education
- Example: Corporate
Someone who completed a 5K race tends to receive recommendations fitting the next level of that trajectory, such as 10K races, preparatory experiences, or complementary events.As new completions are recorded, the recommended progression evolves accordingly.
The engine considers the achievement history as a whole, not just an isolated action. This helps keep recommendations more consistent over time.
Skill Trees and connections between events
The recommendation engine operates on three complementary fronts.Explicit connections (Skill Trees)
Issuers can structure their events into visual Skill Trees with relationships such as:| Type | Meaning |
|---|---|
| Continuation | Direct next step in the same path (one per source node) |
| Prerequisite | A stage that must be completed before a later event |
| Deepening | An expansion of a topic already started |
| Alternative | A valid parallel path toward the same objective — strongly recommended alongside the main route |
| Suggestive | A loose thematic connection with no direct progression link |
Intelligent discovery
Even without explicit connections between events, the engine identifies proximity between opportunities based on context, theme, skills, format, and other relevance signals. This includes two automatic mechanisms:- Content similarity: events with similar skills, keywords, and categories are connected through AI analysis
- Structural similarity: if two events are similar and each leads to a next step, those next steps are also considered similar — even across different issuers
Behavioral mining
The platform also learns from actual participant progression patterns. When many users complete Event A and then complete Event B, that transition is identified and incorporated into recommendations — even if the issuers haven’t created an explicit connection. In other words: today’s achievement improves the chance of finding the right opportunity tomorrow.Value for issuers
For issuers, the recommendation engine is not just an experience layer. It is a lever for distribution and recurrence. Every published event and every issued achievement increase the network’s intelligence and the platform’s ability to:- reconnect participants to new opportunities
- distribute events with greater relevance
- increase progression between stages of a path
- reduce dependency on isolated acquisition
- turn certificates into re-engagement
- create a calendar that keeps working after issuance
Value for achievers
For achievers, the engine reduces friction and increases clarity. Instead of relying solely on manual search or random discovery, the person starts receiving recommendations more compatible with:- what they’ve already done
- what they’ve already completed
- what they want to develop
- the format they prefer
- where they are right now
Feedback and continuous refinement
The engine also learns from interaction signals. In the recommendations area, the user can indicate interest, remove irrelevant suggestions, and adjust their own direction over time. This helps the platform refine future recommendations without relying on public exposure of personal data.Personal goals
Beyond the achievement history, the platform can also consider goals declared by the user themselves. These goals help steer recommendations around explicit intentions, such as developing a skill, advancing a level, switching fields, or deepening a particular area of training. This way, the recommendation doesn’t just look at the person’s past. It also considers where they want to go.At That’s Me, intelligence doesn’t exist to end the journey at a record. It exists to turn every achievement into context, every context into discovery, and every discovery into the next step.