pranshurastogi29/Amazon_ml_challenge-solution
26th place solution from 3290 teams held on HackerEarth
This project provides a highly effective method for classifying short text descriptions, such as product titles or user queries, into predefined categories. By transforming text into numerical representations and applying a specialized classification algorithm, it takes raw text as input and outputs a predicted category or label. This solution is ideal for data scientists or machine learning engineers working on e-commerce product categorization, content moderation, or any task requiring accurate text classification with limited computational resources.
No commits in the last 6 months.
Use this if you need to classify short text data efficiently and achieve strong performance, particularly when computational resources like GPUs are constrained.
Not ideal if you require extensive fine-tuning of large language models on custom datasets, as this solution focuses on efficient methods rather than deep model training.
Stars
7
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 10, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/pranshurastogi29/Amazon_ml_challenge-solution"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
varunkumar-dev/TransformersDataAugmentation
Code associated with the "Data Augmentation using Pre-trained Transformer Models" paper
styfeng/DataAug4NLP
Collection of papers and resources for data augmentation for NLP.
Akshint0407/Automated-Answer-Checker
AI-powered grading system for educators 🔹 Streamlit web app that automates answer sheet...
Anjum48/commonlitreadabilityprize
4th Place solution for the Kaggle CommonLit Readability Prize
yuchen0515/2022-Competition-CUDAOutOfMemory
Our team placed 6th out of 119 teams in E.SUN AI Open Competition Summer 2022 - ASR...