By The MyCheekyDate Team | Based on Smart-Card data across 26,000+ verified events in 65+ cities since 2007
Start with the assumption almost every dating technology makes without saying it out loud: that chemistry can be predicted before two people are ever in the same room.
A profile goes in. An algorithm scores it against other profiles. A match comes out, before either person has said a word to the other, laughed at a bad joke, or noticed the way someone's whole face changes when they talk about something they actually love.
We think that's working from the wrong starting point. And after 19 years in business, with 26,000+ verified events run in just the last 10 years alone, we finally have enough data, and enough machine learning built on top of it, to explain exactly why.
🎭 Every Dating App Starts With a Performance
Here's the thing nobody in dating tech likes to say plainly: a profile is not a person. It's a person's highlight reel, edited for an audience of strangers who will judge it in under two seconds. The best photo. The bio line workshopped until it sounds effortless. The five interests picked because they sound interesting rather than because they're the ones that actually come up on a Tuesday night.
Train an algorithm on that, and you don't get a system that understands attraction. You get a system that's extremely good at predicting who performs well on paper together. Two people who'd talk for hours in person can score badly because neither one's bio used the right words. Two people who'd never make it past a swipe can look perfect on paper, because a good photo is not the same thing as a good conversation.
This is the entire premise the Smart-Card was built to reject. Not a better prediction. No prediction at all. Real observation, from a real conversation, learned across more real conversations than any single app has ever had access to.
📋 What Goes Into the Smart-Card Before the Conversations Begin
Registration for a MyCheekyDate event asks for one thing beyond the basics: your name and email address. That is it. No profile to optimize. No photo to agonize over. No list of interests curated for a stranger's approval.
The bio comes later. And the timing matters more than it might seem.
At the event itself, before the conversations begin, daters enter a short bio directly into the Smart-Card. A few lines, written in the room, on the night, without the hours of refinement that a dating profile at home on a laptop tends to accumulate. No time to workshop it. No opportunity to run it past a friend for feedback. Just a few honest sentences about yourself, written in the moment, before you have met anyone.
This is the first distinction from how most matching technology works. The bio that feeds the Smart-Card machine learning is not a carefully constructed piece of personal marketing. It is something closer to what you would actually say if someone asked you to describe yourself in sixty seconds before walking into a room full of strangers.
That difference in bio authenticity is not a small one. It is the foundation the rest of the data sits on.
📱 What the Smart-Card Actually Does in the Room
The front end is deliberately simple.
After each four-minute conversation at a MyCheekyDate event, you privately rate the person you just spoke with across five tiers. A spectrum of genuine interest that captures not just whether you would like to see someone again, but how strongly you felt that. The selection window stays open until midnight, so there is no pressure to decide on the spot, in the room, with the other person still nearby.
That five-tier rating is the first of four distinct data signals the machine learning collects from every event.
What is happening underneath is where the intelligence lives.
🧠 The Four Signals That Make the Machine Learning Work
This is the part that separates the Smart-Card from anything else in the dating technology space. Not just what it collects, but how many simultaneous signals it cross-references to build a genuinely accurate picture of real-world attraction.
Signal One: Who you selected, and how strongly
Your five-tier ratings for each person you met reveal something no stated preference ever could: who you were actually drawn to, in person, after a real conversation. Not who you thought you would like based on a photo. Not who fit your stated criteria. Who actually held your attention across a table for four minutes and made you want more time.
Signal Two: Who selected you, even when it was not mutual
This is the signal most dating technology ignores entirely, and it may be the most revealing one.
If someone chose you and you did not choose them back, that selection still tells the machine learning something important. It generates a question worth answering: what was it about you, your bio, your conversation style, your presence, the specific attributes you brought to that event, that attracted that particular person? Was it something in how you described yourself? The venue? The age bracket? The time of year?
Every one-sided selection is a data point about what you project, not just what you prefer. The machine learning cross-references those signals against every other data point collected that evening to identify patterns. Over thousands of events, those patterns become precise.
Signal Three: What the mutual matches have in common
When two people both selected each other, the system examines why. What did their bios share? What attributes connected them? What does this mutual match look like compared to the thousands of mutual matches that came before it?
This is where the machine learning earns its name. Repeated across 26,000+ events, the system has built a genuine understanding of what predicts mutual attraction in real-world settings. Not compatibility scores assigned before anyone has spoken, but patterns extracted from conversations that already happened.
Signal Four: The gap between what you said and what you did
Perhaps the most powerful signal of all.
At the event, you wrote a few lines about yourself and what you are looking for. After the event, your selections showed what you actually responded to. The machine learning holds both of those things at once and looks at the gap between them.
People usually are not wrong about what they say they want. They are incomplete. The bio is a guess about yourself. The Smart-Card selection, made privately after a real conversation, is evidence. Across the full dataset, the gap between those two things is consistent, significant, and enormously useful for everything that happens next.
🔒 Why Private Selections Produce Better Data
All four of those signals depend on one thing: honesty.
When selections are visible, even partially, people stop being honest. They start managing how a "no" will land. They soften ratings, hedge choices, avoid the cleaner signal in favor of the socially safer one. A dataset built on strategic, self-conscious answers teaches a machine learning system to model strategy. Not attraction.
Private selections remove that filter entirely. Nobody sees your ratings. Not the host. Not the staff. Not MyCheekyDate internally. The only output that ever surfaces to another person is a mutual introduction, when both people independently and privately chose each other.
One-sided interest produces nothing visible. No notification to the other person. No hint. No nudge. Just silence, unless it is mutual.
Privacy by design produces honest signal. Honest signal is the only kind worth training a system on.
📊 What the Machine Learning Actually Learns Over Time
Aggregated and anonymized across events, the four signals combine to surface patterns that no dataset built from static profiles could ever reach.
The revealed preference gap is consistent and significant. Across the full dataset, there is a reliable difference between the attributes people describe at the event and the attributes that actually predict who they select after a real conversation. This gap is not random. It follows recognizable patterns that the machine learning has become increasingly accurate at identifying.
Behavioral signals outperform demographic ones. How strongly someone rates another person, whether they return for a second event, how their selections shift across an evening, these behavioral signals tend to predict genuine long-term interest more reliably than the static attributes a profile-first system would weight most heavily.
Accuracy compounds over time. Attendees who return for a second event see a 77% improvement in match rate over their first. Some of that is comfort and familiarity with the format. Some of it is the system developing a clearer read from a richer behavioral dataset. With 26,000+ events logged in the last decade alone, that compounding has moved fast.
Nationally, those four signals combine to produce an 86% mutual match rate, averaging 2.3 mutual matches per event. Numbers that reflect conversations that already happened, not compatibility scores for conversations that might.
Honest caveat, the way we treat every number we publish: this is observational data drawn from real event outcomes, not a controlled experiment. It tells you what correlates with stronger matches across thousands of people. It is not a guarantee for any one evening. Strong compass, not a script.
🌐 The Smart-Card Is Not Just an Event Feature. It Is the Intelligence Layer Behind Everything We Do.
Here is the part most people miss when they first encounter the Smart-Card: it was never built to just run one evening well.
Most dating companies offer one product. A speed dating night. A swipe feed. A single format, repeated. The Smart-Card is different. It is the connective intelligence underneath an entire ecosystem, and the speed dating event is simply the front door. Every product beyond that door gets smarter because of what the machine learning has already observed in the room.
This is also where the comparison with other matching technology becomes most clear.
Some platforms use algorithms to narrow who you meet before the event starts, based on preferences you entered at sign-up. It is a defensible philosophy. Filtering the field in advance can spare people conversations that were never going to go anywhere.
The Smart-Card does the same thing, but for everything that comes after the event, and with a dataset that is categorically richer. Rather than filtering future introductions based on what you told us at registration, we filter them based on what your behavior across a real evening actually revealed. Who you chose. Who chose you. How strongly. Where the patterns overlap. What the gap between your bio and your actual selections tells us about who you are genuinely drawn to.
The same intelligence that runs the speed dating matching feeds directly into:
Curated Introductions. Private, one-to-one introductions made outside of events, informed by real behavioral data rather than a registration form. A bio written in the moment is a starting point. A Smart-Card selection, made privately after a real conversation, is evidence. Curated Introductions are built on the evidence.
Luxury Matchmaking. High-touch, personalized matchmaking for discerning singles who want a more considered process. Most luxury matchmakers work from interviews and professional intuition. That is a defensible way to work. It is also, at its core, still working from self-report. Our luxury matchmaking starts from a different position entirely: real behavioral data observed across thousands of evenings, applied to a highly personalized introduction process. That combination is not something a matchmaker without our event history can replicate, regardless of their skill or experience.
CheekySocial. Ongoing social connections informed by Smart-Card behavioral signals, extending the intelligence beyond a single event into a broader social ecosystem.
Singles Events for Business Professionals and Speed Networking. Curated professional gatherings where Smart-Card data informs room composition, so the mix of people reflects patterns the machine learning has already identified as producing strong connections, professional and personal.
Activity-Based Social Events. Interest-aligned gatherings shaped by behavioral attraction patterns rather than a simple shared-hobby filter, built around what the data shows actually brings the right people together.
Invite-Only Private Club Events. Exclusive experiences built around compatibility patterns the machine learning has already identified across thousands of prior evenings. Rooms curated with the benefit of everything the Smart-Card has already learned.
The moat, stated plainly: any company can host a speed dating event. Any company can call itself a matchmaker. No other company in the world has 19 years of real-world attraction data, 26,000+ verified events of machine learning built on top of it in the last decade alone, and a full ecosystem of products that gets smarter with every single evening it runs.
The event is where the data gets made. Everything downstream is where it gets used.
🏙️ What 26,000 Events Teaches That No App Dataset Can Replicate
A swipe dataset, however large, is built from static images and short bios. A few seconds of judgment, repeated millions of times. Wide, but shallow. It has never watched two people's body language shift mid-conversation. Never seen a room's match rate move because the energy changed after 9pm. Never captured the gap between someone who says they want a good listener and what their actual selections, event after event, say they are genuinely drawn to.
26,000+ verified events across 65+ cities is a different kind of dataset. Not wider, but deeper. It is 10 years of real interactions, each one producing signals that only exist because the interaction actually happened. That is not something any app can shortcut its way into. It has to be lived, one real conversation at a time.
💛 One Last Cheeky Thought
Every dating app you have ever used has, at some point, asked you to describe yourself in a way that sounds appealing to a stranger. The Smart-Card asks you to do the same thing, but in the room, on the night, before you have met anyone, with no time to overthink it. And then it watches what actually happens when the conversations begin.
That gap, between what you wrote and who you chose, is where the real learning lives.
CitySwoon learns from what you tell it before the event. MyCheekyDate learns from what you do, who you chose, and who chose you. After 26,000+ events, we know the difference is enormous.
Prediction guesses. Observation learns.
We know which one we would rather be trained on.
Curious what the Smart-Card actually looks like in your hand at an event? Here is the full breakdown. Ready to see where the machine learning leads next, from your first event through to Curated Introductions and Luxury Matchmaking? Find your city and start at the front door: mycheekydate.com.
A Note on Methodology
National baseline figures (86% mutual match rate | 2.3 average matches per event | 77% second-event improvement) reflect the full Smart-Card dataset across all markets, weighted toward the most recent 24 months where sample size allows. Stated vs revealed preference patterns are drawn from event bio inputs compared against private Smart-Card selections. MyCheekyDate was founded in 2007 and has been operating for 19 years. The 26,000+ verified events referenced throughout this piece were run in the last 10 years alone. Full Smart-Card methodology available at mycheekydate.com/smart-card.