paper reading RecSys DS competition

2019-Session-based Item Recommendation with Pairwise Features

Posted by Xiaoye's Blog on April 9, 2023

Table of Contents

  1. Problem Definition
  2. Previous Methods & new Methods
  3. Impacts
  4. TODO & Questions & Further Reading

Problem Definition

  1. Main objective:
  2. Main metrics: MRR

Previous Methods & new Methods

Impacts

  1. 3rd position in competition
  2. Features related to last items are important
  3. FFM, DIEN and ranker are tried but worse than XGB or LightGBM. Pointwise model with well-designed pairwise feature has the best performance

TODO & Questions & Further Reading

  1. XGB -> how to use embedding features
  2. re-check the features
CATALOG
    FEATURED TAGS
    machine learning paper reading 学习笔记-course note Industry RecSys data structure & algorithms deep learning 公开课-MOOC Airbnb pricing Python causal inference deep reinforcement learning leetcode candidate generation item2vector position bias representation learning travel