← Back
Home › Systems › Payments and commerce

publisher-ad-server

Payments and commerce | publisher-ad-server — publisher ad server: line items and guaranteed deals, availability forecasting, delivery pacing, frequency caps, header bidding and dynamic allocation against exchange bids

Google Ad Manager, Kevel, Equativ, FreeWheel

SystemTechniques · 9Primitives · 37 publisher-ad-server Header biddingeconomics · medium: Client or server runs parallel bid requests to many demand partners under a timeout, then picks the winner in a unified auctionBudget pacingfinance · medium: Spreading an advertiser budget over the day via throttling or bid multipliers with a feedback controllerRanked-slot auction (GSP and VCG)finance · medium: Rank bidders by bid × quality, give them the k positions in order, and charge each the minimum bid that would keep their rank (GSP); VCG is the truthful reference.›Feature interaction modelsmachine-learning · medium: Click/conversion prediction networks for ranking: feature crosses (DCN, DeepFM), embedding bags, calibrationMulti-armed banditsmachine-learning · medium: Choose among K options repeatedly while learning their payoffs: epsilon-greedy, UCB1 and Thompson sampling keep total regret low where a fixed split or a fixed exploration rate pays forever.›Supply demand contract allocationoptimization · medium: Allocate forecast supply across contracts with delivery guarantees by flow or dual-based online allocationDeduplicated reach estimationstatistics · medium: Model deduplicated reach and frequency across channels from panel data (beta-binomial / Dirichlet reach curves, overlap calibration)Sliding-window counterssystems · low: Count events in the last W seconds with a ring of sub-bucket counters; the two-bucket weighted estimate gives rate limits in 16 bytes per key.›Feature hashing (the hashing trick)machine-learning · low: Hash each feature name to an index in a fixed-size vector, with a second hash for the sign, so no vocabulary is needed and memory is fixed.›Count-min sketchdata-structures · low: d rows of w counters estimate any item's frequency in a stream, overestimating by at most ε·N with probability 1-δ, in fixed tiny memory.›HyperLogLogdata-structures · low: Counts distinct elements in kilobytes with about 1 % error by tracking the longest run of leading zero bits in hashed values per bucket.›Event deduplication windowdistributed · low: Keep the ids of recently accepted events for a time window and drop repeats; memory stays bounded by rotating time buckets instead of per-entry timers.›Sealed bid auctionfinance · low: First-price and second-price sealed-bid auctions with reserves and floorsSimplex methodoptimization · low: Solves linear programs by walking along the edges of the feasible polytope from vertex to vertex, one basis swap (pivot) at a time; the workhorse behind MIP solvers.›Consent signal propagationsecurity · low: Carry user consent choices as encoded strings (TCF, GPP, GPC) with each request and enforce them per purpose and vendorPID controllerrobotics · low: Drive a measured value to a setpoint with three terms on the error: proportional, integral, derivative. The default feedback loop for motors, heaters, drones and gimbals.›Money representationfinance · low: Store money as integer minor units with an explicit currency exponent, compute in wider integers, and round once with a named rounding mode.›Top-k selectionsearch-sort · low: Keep the k best of n items without sorting all n - bounded min-heap for streams, quickselect for arrays, threshold pruning to skip most items.›Calibrationmachine-learning · low: Make predicted probabilities match observed frequencies: measure with ECE, fix post hoc with temperature, Platt or isotonic scaling on held-out data.›Embeddingsmachine-learning · low: A learned table mapping discrete ids to dense vectors: gather forward, sparse scatter-add backward, row-wise optimizers to keep huge tables cheap.›Loss functionsmachine-learning · low: The scalar a model minimizes: cross-entropy for classes and tokens, MSE or Huber for values, each with a stable form and simple gradient.›PRNGs (PCG, xoshiro)numerics · low: Small, fast, statistically strong non-cryptographic generators: PCG32 and xoshiro256**, with seeding, parallel streams and unbiased ranges.›Bayesian rate estimationstatistics · low: Estimate a conversion or event rate from few observations with a Beta-Binomial or Gamma-Poisson update: two counters, an honest interval, and P(B beats A) directly.›+ 2 more techniques+ 21 more primitives

Similar systems

Share the most building blocks with this one.

ads-auction 21 %demand-side-platform 20 %