ChenglongChen/kaggle-CrowdFlower
1st Place Solution for CrowdFlower Product Search Results Relevance Competition on Kaggle.
Employs XGBoost with linear boosting and extensive feature engineering (SVD, bag-of-words) on search query-product pairs, with a modular pipeline for feature generation, hyperparameter optimization via Hyperopt, and model selection. Final winning solution uses median ensemble aggregation across 35 best-performing models to reduce overfitting and improve generalization on relevance scoring tasks.
1,775 stars. No commits in the last 6 months.
Stars
1,775
Forks
654
Language
C++
License
—
Category
Last pushed
Sep 25, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ChenglongChen/kaggle-CrowdFlower"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ChenglongChen/kaggle-HomeDepot
3rd Place Solution for HomeDepot Product Search Results Relevance Competition on Kaggle.
ai-forever/digital_peter_aij2020
Materials of the AI Journey 2020 competition dedicated to the recognition of Peter the Great's...
minerva-ml/open-solution-avito-demand-prediction
Open solution to the Avito Demand Prediction Challenge
thomasthaddeus/DSComp
This repository is for a sharing work from a competition on kaggle were teamed up on.
DaoyuanLi2816/Kaggle-Eedi-Mining-Misconceptions-in-Mathematics-Silver-Medal
Silver Medal Solution for the Kaggle Competition: Eedi - Mining Misconceptions in Mathematics