CIKM AnalytiCup 2017: Bagging Model for Product Title Quality with Noise
Download as PPTX, PDF
1 like160 views
To stand out from the crowd, sellers employ creative, sometimes disruptive titles for their products in online stores to improve their search relevancy or attract the attention of customers. As a part of the CIKM AnalytiCup 2017, the challenge is to build a product title quality model that can automatically grade the clarity and the conciseness of a product title. Our proposed Bagging Model for Product Title Quality with Noise could leave others behind in performance and become the winner of the CIKM Cup 2017 competition.
CIKM AnalytiCup 2017: Bagging Model for Product Title Quality with Noise
- 1. Photo By: David Doubilet
- 2. CIKM AnalytiCup Lazada Product Title Quality Challenge 1 $6,000 2$2,000 3$1,000 $2,000
- 3. Team Members Tam T. Nguyen nthanhtam@gmail.com Postdoctoral Research Fellow Ryerson University Kaggle Grandmaster Hossein Fani hosseinfani@gmail.com PhD Student University of New Brunswick Gilberto Titericz giba1978@gmail.com Machine Learning Expert AirBnb Inc. Kaggle Grandmaster Ebrahim Bagheri ebrahim.bagheri@gmail.com Associate Professor Ryerson University
- 4. Photo By: Justin Hofman
- 5. hot sexy red clutch rug sack travel backpack unisex cheap with free gift 1 clarity 2 conciseness Hot Sexy Tom Clovers Womens Mens Classy Look Cool Simple Style Casual Canvas Crossbody Messenger Bag Handbag Fashion Bag Tote Handbag Gray Problem Setting
- 6. Photo By: David Doubilet
- 7. Clarity if within five seconds one can understand the title, what the product is, and quickly figure out the key attributes (color, size, model, ...). Conciseness if it is short enough to contain all the necessary information. Otherwise, i.e., the title is too long with many unnecessary words, Or it is too short such that it is unsure what the product is. Data Set
- 9. ML-DM 1. Cleansing Noise Missing Values Outliers 2. Flirting Attributes Labels (if any) Augmentation 3. Feature Eng. Extraction Reduction Selection 4. Model Eng. Selection Tuning Evaluation
- 10. 1. Cleansing Noise Html tags in short_description (%94) Missing Values product_type (less than %1) category_lvl_3 (about %6) assign category_lvl_2 description (less than %1) Outliers price {-1, 999999, 9999999}, price Normalization based on country
- 11. 2. Flirting Attributes Color Brand Non-English <img> Image <li> enumeration : Labels Disagreement in labels!(label noise) Augmentation Cloning color, brand
- 12. Label Noise
- 14. multi-class : 1 2 : 1, 2, , binary(boolean) classifier: : 0,1 multi-output(label) : 1 2 1: 1, 2, , 1 2: 1, 2, , 2 : 1, 2, , r multi-output binary(boolean) classifier: 1: 0,1 2: 0,1 Targets correlation: (single, fast model for all targets) Only 3 combinations for (Clear,Concise): (1,0), (1,1), (0,0) |~Clear & Concise|= 0 if ~Clear then ~Concise if Concise then Clear
- 16. 3. Feature Eng. Extraction Reduction LSA,T-SNE,PCA,SVD Selection STD Correlation X~y Linear(t-test, chi2) Non-linear(mi) Model-driven LinearSVM Feature Engineering
- 19. 10-Fold Set 1 10-Fold Set 2 10-Fold Set 3 10-Fold Set 4 Base Model Ensemble Model Final Prediction Fold Bagging Fold Bagging Set Fold Bagging BLENDBLEND BLEND BLENDSTACK STACK STACK STACK BLENDBLEND BLEND BLEND BLEND Bagging Models
- 20. Performance Evaluation SGD: stochastic gradient descent LOR: logistic regression RDG: ridge regression NBC: naive bayes classifier XGB: extreme gradient boosting LGB: light gradient boosting W2V: word2vec
Editor's Notes
- #4: On Lazada, we have millions of products across thousands of categories. To stand out from the crowd, sellers employ creative, sometimes disruptive efforts to improve their search relevancy or attract the attention of customers. Product titles like this degenerate user experience by cluttering the site with irrelevant, misleading titles. In this challenge, we provide you with a set of product titles, description, and attributes, together with the associated title quality scores (clarity and conciseness) as labeled by our internal QC team. Your task is to build a product title quality model that can automatically grade the clarity and the conciseness of a product title. judging a book by its cover
- #6: On Lazada, we have millions of products across thousands of categories. To stand out from the crowd, sellers employ creative, sometimes disruptive efforts to improve their search relevancy or attract the attention of customers. Product titles like this degenerate user experience by cluttering the site with irrelevant, misleading titles. In this challenge, we provide you with a set of product titles, description, and attributes, together with the associated title quality scores (clarity and conciseness) as labeled by our internal QC team. Your task is to build a product title quality model that can automatically grade the clarity and the conciseness of a product title. judging a book by its cover
- #15: Contraposition Use one target as a feature for the other one. But has problem in practice since we dont have the validation or test sets label.
- #17: Plus the attributes, we extract more features from the textual attributes, title and short_description stability selection recursive feature elimination and cross-validation