Implementation of Unsupervised k-Means Clustering Algorithm Within Amazon Web Services Lambda

This work demonstrates how an unsupervised learning algorithm based on k-Means Clustering with Kaufman Initialization may be implemented effectively as an Amazon Web Services Lambda Function, within their serverless cloud computing service. It emphasizes the need to employ a lean and modular design philosophy, transfer data efficiently between Lambda and DynamoDB, as well as employ Lambda Functions within mobile applications seamlessly and with negligible latency. This work presents a novel application of serverless cloud computing and provides specific examples that will allow readers to develop similar algorithms. The author provides compares the computation speed and cost of machine learning implementations on traditional PC and mobile hardware (running locally) as well as implementations that employ Lambda.