Building an Effective Data Science Practice: A Framework to Bootstrap and Manage a Successful Data Science Practice

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2022

V. Raina, S. KrishnamurthyBuilding an Effective Data Science Practicehttps://doi.org/10.1007/978-1-4842-7419-4_17

17. Inference

Vineet Raina¹   and Srinath Krishnamurthy¹

(1)

Pune, India

 

Once models are created in the machine learning step, they need to be deployed as part of real-world processes and production systems. This is done in the inference step of the data science process.

In the inference step, we perform the tasks required to push the models to the production systems so that they can be used by other applications and to monitor the performance of these models.

Figure 17-1 shows the various activities, techniques, and technologies that go into this ...