Doing research in Machine Learning is certainly very exciting but trying to keep up with the galloping changes in this field can mislead researchers into producing incomplete, inaccurate or sketchy papers. This checklist is based on Michael A. Lones paper titled "How to avoid machine learning pitfalls: a guide for academic researchers", arXiv:2108.02497, v1, August 2021 and aims to help researchers verify that they have adequately conducted the writing of their research by validating it in terms of robustness, rigorousness, completeness and comparability.
This tool can be used while you are working on a research project or at the end of it to make sure that you have done everything correctly and rigorously. The system will return a score for each of the four parameters taken into account, namely Robustness, Rigorousness, Completeness and Comparability.
