---
title: "Vashni Roy (@vashniroy) | Hashnode"
description: "Software Engineer | Full Stack & AI/ML. Read the latest articles by Vashni Roy on Hashnode."
url: "https://hashnode.com/@vashniroy"
---

@vashniroy

# Vashni Roy

@vashniroy · Hyderabad, India · Joined October 2026

Software Engineer | Full Stack & AI/ML

### [Why 0.5 Isn't Always the Right Classification Threshold](https://vashniroy.hashnode.dev/why-0-5-isn-t-always-the-right-classification-threshold?utm_source=hashnode&utm_medium=feed)

I changed the threshold of the same churn model from 0.3 to 0.7. The model stayed the same, but its predictions changed quite a lot.

3 min read · [vashniroy.hashnode.dev](https://vashniroy.hashnode.dev/why-0-5-isn-t-always-the-right-classification-threshold?utm_source=hashnode&utm_medium=feed)

[5h ago](https://hashnode.com/posts/why-0-5-isn-t-always-the-right-classification-threshold/6af2ffa99538fc7c0f2ddfef)

### [Does a More Complex ML Model Actually Give Better Results?](https://vashniroy.hashnode.dev/does-a-more-complex-ml-model-actually-give-better-results?utm_source=hashnode&utm_medium=feed)

I compared Logistic Regression and XGBoost on the same churn dataset. The simpler model performed better, even across 5-fold cross-validation.

3 min read · [vashniroy.hashnode.dev](https://vashniroy.hashnode.dev/does-a-more-complex-ml-model-actually-give-better-results?utm_source=hashnode&utm_medium=feed)

[Oct 14](https://hashnode.com/posts/does-a-more-complex-ml-model-actually-give-better-results/6acf5b94f069b0121b58b0e5)