MapReduce
Noun · Development
Definitions
A programming model for processing large datasets across a cluster, where a Map phase applies a function to each input record to emit key-value pairs, a shuffle phase groups pairs by key, and a Reduce phase aggregates each group into a final result. Popularized by Google's 2004 paper and implemented in Apache Hadoop.
In plain English: A way to process huge amounts of data by splitting the work across many computers: each one processes a piece, then results are combined.
Example: "The word-count MapReduce job maps each line to (word, 1) pairs and reduces by summing the counts."