← Back
Home › Systems › AI applications

realtime-personalization

real-time personalization

Netflix artwork

SystemTechniques · 17Primitives · 41 realtime-personalization 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.›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.›Off policy evaluationmachine-learning · medium: Estimating a new policy's reward from logged data: IPS, self-normalized IPS, doubly robustTwo-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.›HNSWsearch-sort · medium: Hierarchical Navigable Small World: a layered proximity graph searched greedily from a sparse top layer; the default in-memory approximate nearest-neighbour index.›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.›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.›W-TinyLFUsystems · low: An LRU window plus segmented LRU, guarded by a 4-bit Count-Min sketch that admits a newcomer only if it beats the victim's frequency.›Hash 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.›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.›Columnar file formatstorage · low: Row groups, column chunks, pages, encodings and footer stats (Parquet/ORC style) (listed in Moved to the wiki)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.›Linear and logistic regressionmachine-learning · low: Fit a weighted sum of features to a number (least squares) or a probability (logistic); the baseline every model must beat.›Importance samplingnumerics · low: Sample from a proposal distribution and reweight to cut Monte Carlo varianceBootstrap confidence intervalsstatistics · low: Resampling-based confidence intervals for arbitrary statisticsNegative samplingmachine-learning · low: Train by contrasting each observed positive with a few sampled negatives instead of normalising over every candidate; the choice of sampler decides bias and quality.›d-ary heapdata-structures · low: Array heap with d children per node (d = 4 typical): half the binary heap's depth, siblings in one cache line, faster priority queues.›+ 10 more techniques+ 25 more primitives

Similar systems

Share the most building blocks with this one.

recommender 45 %ads-auction 33 %fraud-detection 26 %dynamic-pricing 24 %short-video 23 %