Machine Learning: 2 Books in 1: Machine Learning for Beginners, Machine Learning Mathematics. An Introduction Guide to Understand Data Science Through the Business Application

Infrastructure and resources for data science
projects
To effectively store infrastructure and manage shared analytics, the TDSP
recommends using tools like: "machine learning service", databases, "big
data clusters" and cloud-based systems to store data sets. The analytics and
storage infrastructure that houses raw as well as processed or cleaned data
sets can be cloud-based or on-premises. D analytics and storage
infrastructure permits the reproducibility of analysis and prevents
duplication and the redundancy of data that can create inconsistency and
unwarranted infrastructure costs. Tools are supplied to grant specific
permissions to the shared resources and to track their activity which in turn
allows secure access to the resources for each member of the team.
Tools and utilities for project execution
Introduction of any changes to an existing process tends to be rather
challenging in most organizations. To encourage and raise the consistency
of adoption of these changes several tools can be implemented that are

---

provided by the TDSP. Some of the basic tasks in the data science lifecycle
including "data exploration" and "baseline modeling" can be easily
automated with the tools provided by TDSP. To allow the hassle-free
contribution of shared tools and utilities into the team's "shared code
repository", TDSP from provides a well-defined structure. This results in
cost savings by allowing other project teams within the organization to
reuse and repurpose these shared tools and utilities.
The TDSP lifecycle serves as a standardized template with a well-defined
set of artifacts that can be used to garner effective team collaboration and
communication across the board. This lifecycle is comprised of a selection
of the best practices and structures from “Microsoft” to facilitated
successful delivery predictive analytics Solutions and intelligent
applications.
Let’s look at the details of each of the five stages of the TDSP lifecycle,
namely, “Business understanding”, “Data acquisition in understanding”,
“modeling”, “deployment” and “customer acceptance”.

---