Skip to main content
eScholarship
Open Access Publications from the University of California

UCLA

UCLA Electronic Theses and Dissertations bannerUCLA

An Application of Recurrent Neural Network:Prediction of Items’ Price by Description

  • Author(s): Su, Beichen
  • Advisor(s): Wu, Yingnian
  • et al.
Abstract

In this application, a predictive model is built for finding the price of an item from their characteristics, especially the description. The implementation of word vectors, optimized gradient descent, and long short-term memory are employed to tackle the problem. And the relatively low loss for both training and test set proves this is a reasonable approach.

Main Content
Current View