← Back
Home › Systems › AI applications

ads-auction

ads ranking and auction

Google Ads

SystemTechniques · 21Primitives · 70 ads-auction Windowed stream aggregationdistributed · medium: Group events by event-time window per key, keep one partial aggregate per slice, and emit a window when the watermark passes its end.›Budget 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, calibrationFeature storemachine-learning · medium: One definition per feature feeds a history store for training and a latest-value store for serving, so training and inference see the same values as of the same moment.›Multi-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.›Two-tower retrievalmachine-learning · medium: Two separate encoders map users/queries and items into one vector space; item vectors are precomputed and searched by nearest neighbour, so recall over millions costs one small forward pass.›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.›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.›Double-entry ledgerfinance · low: Append-only journal of transactions whose postings sum to zero per currency; balances are derived, so money can only move, never appear or vanish.›Idempotency keysfinance · low: Client-chosen unique key per logical operation, stored with a request fingerprint and the final response, so retries replay the first result instead of acting twice.›Boolean expression indexingsearch-sort · low: Indexing conjunctive targeting expressions so one event finds all matching ads/subscriptions fastHedged requestssystems · low: Sending a backup request after a latency percentile and taking the first answer to cut tail latencyHash aggregationstorage · low: GROUP BY via hash tables with partitioning and spill to diskHierarchical timing wheelsystems · low: Timers bucketed by expiry into wheels of slots, coarser wheels for far deadlines: O(1) insert and cancel for millions of timeouts.›PID 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.›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.›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.›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.›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.›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.›+ 14 more techniques+ 54 more primitives

Similar systems

Share the most building blocks with this one.

demand-side-platform 34 %realtime-personalization 33 %recommender 31 %fraud-detection 30 %publisher-ad-server 21 %

In-house systems

Named systems of this kind at large companies, with their paper or write-up.

Andromeda (ads retrieval)Meta Platforms