The Path to Predictive Analytics and Machine Learning

Chapter 4. Redeploying Batch Models in Real Time

For all the greenfield opportunities to apply machine learning to business problems, chances are your organization already uses some form of predictive analytics. As mentioned in previous chapters, traditionally analytical computing has been batch oriented in order to work around the limitations of ETL pipelines and data warehouses that are not designed for real-time processing. In this chapter, we take a look at opportunities to apply machine learning to real-time problems by repurposing existing models.

Future opportunities for machine learning and predictive analytics span infinite possibilities, but there is still an incredible amount of easily accessible opportunities today. These come by applying existing batch processes based on statistical models to real-time data pipelines. The good news is that there are straightforward ways to accomplish this that quickly put the business rapidly ahead. Even for circumstances in which batch processes cannot be eliminated entirely, simple improvements to architectures and data processing pipelines can drastically reduce latency and enable businesses to update predictive models more frequently and with larger training datasets.

Batch Approaches to Machine Learning

Historically, machine learning approaches were often constrained to batch processing. This resulted from the amount of data required for successful modeling, and the restricted performance of traditional systems.

For example, ...