LGMar 13, 2022

ORDSIM: Ordinal Regression for E-Commerce Query Similarity Prediction

arXiv:2203.06591v13 citationsh-index: 30
Originality Incremental advance
AI Analysis

This work addresses query similarity prediction for e-commerce platforms to improve monetization by enhancing high-similarity accuracy, representing an incremental improvement over existing regression methods.

The paper tackled the problem of query similarity prediction in e-commerce by proposing ORDSIM, an ordinal regression model that focuses on accurately predicting high-level similarity to boost monetization, achieving substantially smaller prediction error on a dataset of over 10 million queries from eBay.

Query similarity prediction task is generally solved by regression based models with square loss. Such a model is agnostic of absolute similarity values and it penalizes the regression error at all ranges of similarity values at the same scale. However, to boost e-commerce platform's monetization, it is important to predict high-level similarity more accurately than low-level similarity, as highly similar queries retrieves items according to user-intents, whereas moderately similar item retrieves related items, which may not lead to a purchase. Regression models fail to customize its loss function to concentrate around the high-similarity band, resulting poor performance in query similarity prediction task. We address the above challenge by considering the query prediction as an ordinal regression problem, and thereby propose a model, ORDSIM (ORDinal Regression for SIMilarity Prediction). ORDSIM exploits variable-width buckets to model ordinal loss, which penalizes errors in high-level similarity harshly, and thus enable the regression model to obtain better prediction results for high similarity values. We evaluate ORDSIM on a dataset of over 10 millions e-commerce queries from eBay platform and show that ORDSIM achieves substantially smaller prediction error compared to the competing regression methods on this dataset.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes