Kaggle on Veritable Tech Blog

[Kaggle] Quick Recap of Orbit Wars

Fri, 10 Jul 2026 00:00:00 +0000

Reflections on competing in Kaggle's Orbit Wars, from building a Rust simulation engine to learning hard lessons about complexity and prioritization.

[Kaggle] Google Research Football 2020

Mon, 28 Dec 2020 00:00:00 +0000

Describing my 16th place solution and also reviewing some of the others'

[Competition] Jigsaw Multilingual Toxic Comment Classification

Wed, 05 Aug 2020 00:00:00 +0000

The 3rd Jigsaw Text Classification Competition

TensorFlow 2.1 with TPU in Practice

Thu, 13 Feb 2020 00:00:00 +0000

Case Study: Google QUEST Q&A Labeling Competition

[Notes] Jigsaw Unintended Bias in Toxicity Classification

Sun, 04 Aug 2019 00:00:00 +0000

Bias Reduction; Summary of Top Solutions

[Notes] iMet Collection 2019 - FGVC6 (Part 1)

Tue, 16 Jul 2019 00:00:00 +0000

Overview; Augmentation; Training Models on Kaggle

[Review] Kaggle Toxic Comment Classification Challenge

Sat, 24 Mar 2018 05:40:19 +0000

Photo Credit

Introduction

Jigsaw toxic comment classification challenge features a multi-label text classification problem with a highly imbalanced dataset. The test set used originally was revealed to be already public on the Internet, so a new dataset was released mid-competition, and the evaluation metric was changed from Log Loss to AUC.

I tried a few ideas after building up my PyTorch pipeline but did not find any innovative approach that looks promising. Text normalization is the only strategy I had found to give solid improvements, but it is very time consuming. The final result (105th place/about top 3%) was quite fitting IMO given the time I spent on this competition(not a lot).