With the new ability to extend Redis with native modules, we explore the benefits of using them in conjunction with Spark: By storing Machine Learning algorithms’ models in Redis, and using Redis modules, we can offload the processing of these models directly to Redis. This allows fast classification and other processing, without the costs of loading the model data into Spark first. This will cover: * An overview of Redis modules. * How we implemented the technique for selected algorithms. * How we integrated this with Spark. * Benchmark showing the performance gains.
