3 Before you model: Planning and Scoping

This chapter covers

  • How to effectively plan ML projects with a diverse team to reduce the chances of rework or project abandonment
  • Scoping and how to estimate the amount of effort and the minimum number of features required to deliver demonstrations of projects on time and with the least amount of rework

The two biggest killers in the world of ML projects are ones that have nothing to do with what most Data Scientists ever imagine. They aren’t related to algorithms, data, or technical acumen. They have absolutely nothing to do with which platform you’re using, nor with the processing engine that will be optimizing a model. The biggest reasons for projects failing to meet the needs of a business are in the steps leading up to any of those technical aspects: the planning and scoping phases of a project.

Throughout most of the education and training that we receive leading up to working as a DS at a company, emphasis is placed rather heavily on independent work on solving complex problems. Isolating one’s self and focusing on showing demonstrable skill in the understanding of the theory and application of algorithms trains us to have the expectation that the work we will do in industry is a solo affair. Given a problem, we figure out how to solve it.

3.1      Planning: you want me to predict what?!

3.1.1   Basic planning for a project

3.1.2   That first meeting

3.1.3   Plan for demos. Lots of demos.

3.1.4   Experimentation by solution building: wasting time for pride’s sake

3.2      Experimental Scoping: Setting expectations and boundaries

3.2.1   Experimental scoping for the ML team - Research

3.2.2   Experiment scoping for the ML team – Experimentation

3.3      Summary