Too Few People in the Same Room at the Same Time: A Pre-specified Co-Presence Density Test of Closed Venue-Based Dating Apps

No venue-based dating app we found survived on spontaneous check-ins at the same bar or club. We test whether expected mutual matches per participant and check-in evening separate closed products from working in-person formats. Six entries from five of sixteen closed or dormant products were modelled and compared with four working formats, including speed dating and one documented app launch night in a full club. A Monte Carlo co-presence model, a success criterion and eight perturbation scenarios were pre-specified before any model run in an internal, dated protocol, not publicly deposited. The pre-specified strong criterion failed: the best threshold, 0.20 expected matches per evening, separated all closed from all working cases in 73.5% of 2,000 parameter draws, short of the required 80%, and five of eight perturbation scenarios fell below 80%. A post-hoc analysis supports a weaker claim: the five closed check-in or map formats delivered 0.003–0.03 expected matches per evening (medians), below the weakest working format in 99.95% of draws (median gap 1.1 orders of magnitude). They needed roughly 9–13.5 checked-in users per venue and evening but had 0.14–1.7, a gap of 8- to 68-fold. In a descriptive, not pre-specified analysis, documented acquisition campaigns, including one with an estimated 450,000 downloads, moved venue-level density by less than a factor of two. That matching markets need thickness is well known; we contribute a pre-specified, quantitative cross-case test of it for venue-based dating. The results are consistent with working formats succeeding by bundling participants into one time slot. Files: paper (PDF); case table with sources, stored model outputs, model code (seed 20261028), redacted English translation of the internal protocol and LaTeX source (ZIP).

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-15
DOI
https://doi.org/10.5281/zenodo.24247933
Primary Topic
Digital Platforms and Economics
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Too Few People in the Same Room at the Same Time: A Pre-specified Co-Presence Density Test of Closed Venue-Based Dating Apps

Michael Bieg
Zenodo (CERN European Organization for Nuclear Research)
Digital Platforms and Economics
preprint

Too Few People in the Same Room at the Same Time: A Pre-specified Co-Presence Density Test of Closed Venue-Based Dating Apps

Michael Bieg
preprint en

Abstract

No venue-based dating app we found survived on spontaneous check-ins at the same bar or club. We test whether expected mutual matches per participant and check-in evening separate closed products from working in-person formats. Six entries from five of sixteen closed or dormant products were modelled and compared with four working formats, including speed dating and one documented app launch night in a full club. A Monte Carlo co-presence model, a success criterion and eight perturbation scenarios were pre-specified before any model run in an internal, dated protocol, not publicly deposited. The pre-specified strong criterion failed: the best threshold, 0.20 expected matches per evening, separated all closed from all working cases in 73.5% of 2,000 parameter draws, short of the required 80%, and five of eight perturbation scenarios fell below 80%. A post-hoc analysis supports a weaker claim: the five closed check-in or map formats delivered 0.003–0.03 expected matches per evening (medians), below the weakest working format in 99.95% of draws (median gap 1.1 orders of magnitude). They needed roughly 9–13.5 checked-in users per venue and evening but had 0.14–1.7, a gap of 8- to 68-fold. In a descriptive, not pre-specified analysis, documented acquisition campaigns, including one with an estimated 450,000 downloads, moved venue-level density by less than a factor of two. That matching markets need thickness is well known; we contribute a pre-specified, quantitative cross-case test of it for venue-based dating. The results are consistent with working formats succeeding by bundling participants into one time slot. Files: paper (PDF); case table with sources, stored model outputs, model code (seed 20261028), redacted English translation of the internal protocol and LaTeX source (ZIP).

Zenodo (CERN European Organization for Nuclear Research)
Digital Platforms and Economics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon