Published inBetter ProgrammingMy Journey with Depth EstimationI recently participated in the AICrowd Mono Dept Perception competition, a proud milestone in my machine-learning journey. I secured 4th…Jul 15, 2023Jul 15, 2023
Published inTDS ArchiveOn AB tests and Carryover EffectWhat happens when the effects of one AB test bleed into the next, muddying the waters and skewing the results?May 23, 2023May 23, 2023
Should I Use Jupyter Notebooks or Python Scripts for My Next ML Project?In the world of machine learning and data science, two popular tools for working with code are Jupyter notebooks and Python scripts. But…Dec 5, 2022Dec 5, 2022
Published inTDS ArchiveIs Attention Explanation?The problem of models' explanations in machine learning is always present. We want glass-box models for various reasons. First, data…Jun 21, 2022Jun 21, 2022
Published inTDS ArchiveHow to write a Data Science resumeMaximize your chances of being hired with a better-organized CVApr 6, 2021Apr 6, 2021
Published inTDS ArchiveWhat’s Wrong with LIMEWhile being one of the most popular approaches for explaining predictions of any classifier, LIME has several major problems.Sep 7, 2020A response icon1Sep 7, 2020A response icon1
Published inTDS ArchiveStop Permuting FeaturesPermutation importance may give you wrong, misleading results. But why?Jul 27, 2020A response icon1Jul 27, 2020A response icon1
Published inTDS Archivetl; dr: The Clean Coder by Robert MartinSummary of The Clean Coder by Robert Martin for Data ScientistsApr 15, 2020Apr 15, 2020
Published inTDS ArchiveAutoML for Time Series ForecastingThe overview of the 1st place solution in recent AutoML competitionJan 6, 2020A response icon2Jan 6, 2020A response icon2
Published inTDS ArchiveAutoML is OverhypedAutoML as an idea of automating a modeling process is excellent, yet the field is overhyped.Oct 12, 2019A response icon6Oct 12, 2019A response icon6
