Marketplaces & Two-Sided Platforms// topic
Matching, ranking and dispatch
In short
How supply actually meets demand — matching and dispatch algorithms, the ranking signals behind result order, fairness in how leads are distributed, and what changes when the binding constraint is time, distance or a thin seller pool.
6 pages
diagnostics
- A handful of sellers are taking everything: is it the ranker or the market?Concentration is only a defect if your ranker built it. Re-rank the same queries with every history-derived signal removed, and the share distribution tells you which answer you have.diagnostic9 min
- Matching got slower as supply grew: which stage stopped being linearPlot each stage's duration against candidate-set size on log-log axes. The slope names the stage that stopped being linear, and each stage has a structurally different repair.diagnostic9 min
definitions
- Acceptance rate: what it measures, and when it measures the platformAccepted over offered sounds like a measure of a seller. The platform chooses the denominator, so an uncorrected acceptance rate is partly a measure of your own targeting.definition7 min
- Dispatch radius: a travel-time boundary that only looks like a circleThe circle on the map is a proxy. The real boundary is however far a provider can travel in an acceptable time, which is different in every direction and at every hour.definition7 min
- Lead distribution: the four shapes a request can reach sellers inBroadcast, sequential offer, shortlist, exclusive assignment. The shapes differ in who pays when nobody answers, which is also the question that identifies yours.definition7 min
- Signal, score and sort order: three layers people keep collapsingA signal is a measurement, a score is policy and a sort is a product rule that can ignore both. Most ranking arguments are two people proposing changes at different layers.definition7 min
Other topics in Marketplaces & Two-Sided Platforms
See allMarketplace architecture and the transaction data modelThe schema and state machines underneath every marketplace — listings, availability, holds, orders and the transitions between them — and the modelling decisions that are expensive to reverse once real supply is on the platform.7 pagesSplit payments, payouts and the money ledgerMoney movement in a multi-party transaction — split charges and commission, delayed release, refunds and partial refunds, wallets and credits, and the double-entry ledger that has to reconcile with the processor every single day.1 pageBuild versus buy, platform choice and scopingThe decision made before any code — what Sharetribe, Marketplacer, Mirakl or a multi-vendor Shopify app really give you and exactly where they stop, what genuinely drives marketplace scope, and how to brief the work so it can be estimated at all.1 page
Working on something in this space?
Tell us where you are in a sentence or two. We'll tell you honestly whether we're the right team, and what a sensible first slice of the work looks like.
Start the conversation