liveBook · Manning

Pre-project data investigation

As explained in Delivering Machine Learning Projects: From design to deployment

A pre-project data investigation is an inquiry performed before formal project execution to establish what data exists, how it can be used, and what risks it presents.

A pre-project data investigation establishes what data exists, how it can be accessed and assembled, and whether its use is ethical and legal before formal ML execution. section 4.5

Turn the investigation into explicit delivery work:

  • Obtain a data sample during pre-sales, then use protected commercial access in sprint 0 to understand the customer’s data. section 4.5
  • Build a narrative about the operating domain and identify the tables, resources, and fragmented sources needed for modeling. section 4.5
  • Create a system-facing data survey in sprint 1 before modelers perform exploratory data analysis. section 4.5

Data story ticket

Record the investigation as “Undertake a pre-project data investigation,” linking the available sample, access conditions, ethical and legal checks, resource inventory, and unresolved assembly problems. section 4.5

How Delivering Machine Learning Projects: From design to deployment covers it

How deep it goes
Traces samples, access, governance, domain narrative, resource surveying, and EDA sequencing, but stops short of detailed analytical methods.
Examples
Uses a data sample, a data story ticket, a resource survey, and assembled tables from fragmented sources.
What it assumes
Assumes a customer, a project mandate, a data sample or access path, and awareness that modeling depends on available data.
What you can do after
Evaluate/understand available data, access constraints, ethical and legal risks, and readiness for exploratory analysis.
How it connects
Connects data samples, sprint 0, sprint 1, data surveys, exploratory data analysis, data modeling, and ethics.
Cover of Delivering Machine Learning Projects: From design to deployment
liveBookmanning.com
Read Delivering Machine Learning Projects: From design to deployment on liveBook Get the book at manning.com

This explainer was generated by Manning's knowledge graph from the text of Delivering Machine Learning Projects: From design to deployment. The section links point to the parts of the book it draws on.