DOI: https://doi.org/10.15368/theses.2021.85
Available at: https://digitalcommons.calpoly.edu/theses/2604
Date of Award
6-2021
Degree Name
MS in Computer Science
Department/Program
Computer Science
College
College of Engineering
Advisor
Alexander M. Dekhtyar
Advisor Department
Computer Science
Advisor College
College of Engineering
Abstract
Many consumer facing companies have large scale data sets that they use to create recommendations for their users. These recommendations are usually based off information the company has on the user and on the item in question. Based on these two sets of features, models are created and tuned to produce the best possible recommendations. A third set of data that exists in most cases is the presence of past interactions a user may have had with other items. The relationships that a model can identify between this information and the other two types of data, we believe, can improve the prediction of how a user may interact with the given item. We propose a method that can inform the model of these relationships during the training phase while only relying on the user and item data during the prediction phase. Using ideas from convolutional neural networks (CNN) and collaborative filtering approaches, our method manipulated the weights in the first layer of our network design in a way that achieves this goal.