Yash Agarwal

Sep 29, 2024 | medium.com | Yash Agarwal

Why is it important and how do we come up with that formula? Yash Agarwal·Follow6 min read·--UnsplashWhen dealing with sequential data like text, the order of words carries crucial information. The sequence in which words appear can change the meaning entirely, such as the difference between “dog bites man” and “man bites dog”.

Sep 20, 2024 | medium.com | Yash Agarwal

In early 2024, during the final semester at BITS, I joined the design team at Disney+ Hotstar. I was eager to work on a platform with such a massive user base, and the experience was everything I hoped it would be and more. Here are some of my key learnings —User-Centered Design is more than just theoryOne of the first things I learned was the importance of truly understanding how users interact with our product.

Aug 5, 2024 | mytravaly.com | Yash Agarwal

Whether you're planning your honeymoon or a special romantic escape, Singapore offers a plethora of enchanting spots perfect for creating lasting memories. If you’re considering Singapore honeymoon packages, here’s a guide to some of the most romantic places to visit in this vibrant city-state. 1. Gardens by the BayGardens by the Bay is a must-visit for couples looking to immerse themselves in a futuristic garden paradise.

Jun 17, 2024 | medium.com | Yash Agarwal

Tree boosting algorithms are highly effective and widely used in Machine Learning. They have been the key to winning many Kaggle competitions and consistently produce state-of-the-art results. Among these, XGBoost, or Extreme Gradient Boosting, stands out as one of the most popular and powerful algorithms.

Jun 14, 2024 | medium.com | Yash Agarwal

In machine learning, ensemble techniques often outperform traditional algorithms like Regression and SVM. These techniques combine the predictions of multiple models to produce more accurate results. Ensemble methods come in two main types: bagging and boosting. Bagging, short for Bootstrap Aggregating, involves training multiple models on different subsets of the data. The final prediction is made by averaging or voting on the results of these models.