Assignment 1 Linear Modelling with Sales Data

Developing linear models with R to make sales predictions and creating a report that engaged the audience while communicating outcomes

profile picture of author
Author
Joshua McCarthy
Published
Sun, Apr 19 2020
Last Updated
Sun, Apr 19 2020

Context

This assignment was a first chance to experiment with linear models for a business challenge. Reading through the brief and based on the instructors comments, I felt that, while the technical challenge of delivering an accurate prediction for next month is important, an equal amount of value was being placed on our ability to communicate effectively with the audience and reflected a real world output.

Using all the notes and answers you have above, wrap up all your work into a report for the manager of the automotive firm that follows the CRISP-DM methodology. Remember to consider your audience!

I saw this as an opportunity to experiment with how I might develop a data science focused but user accessible report. Dedicating a portion of the exploration time to evaluating the needs of a sales manager in this context, drawing on professional experience and a needs, wants, solutions design framework.

Report

The report appendices with predictions has been omitted

Report Page 1, problems, solutions, predictive modelling

Report Page 1, problems, solutions, predictive modelling

Report Page 2, understanding from data, clients, billables, security

Report Page 2, understanding from data, clients, billables, security

Report Page 3, variable evaluation detail, linear modelling process, rmse

Report Page 3, variable evaluation detail, linear modelling process, rmse

Report Page 4, outcomes, deliverables, effects of variable engineering, 46% predictions less than 15% RMSE

Report Page 4, outcomes, deliverables, effects of variable engineering, 46% predictions less than 15% RMSE