Introduction

In this final chapter, we will focus on working on a research-based capstone project. The ideas from all the previous chapters such as designing the problem using the SCQ framework, identifying the source of data, preprocessing the dataset, training a machine learning model, evaluating a model, applying resampling techniques, and many other concepts will be used. Additionally, this chapter will also focus on benchmarking models, designing experiments in machine learning, collaborating in open source platforms, and making a research work reproducible for the benefits of the larger community.

The abundance of online resources, computation power, and out-of-the-box toolkit solutions has made the entry barrier in becoming a machine learning professional minimum. Today, we have plenty of quickstart algorithms provided as a function in a package in programming languages such as R and Python, or even as a drag and drop in platforms such as Google Cloud AutoML or Microsoft Azure Machine...