Matching Items (2)
Filtering by
- All Subjects: artificial intelligence
- Member of: Theses and Dissertations
- Member of: Barrett, The Honors College Thesis/Creative Project Collection
Description
In the age of information, collecting and processing large amounts of data is an integral part of running a business. From training artificial intelligence to driving decision making, the applications of data are far-reaching. However, it is difficult to process many types of data; namely, unstructured data. Unstructured data is “information that either does not have a predefined data model or is not organized in a pre-defined manner” (Balducci & Marinova 2018). Such data are difficult to put into spreadsheets and relational databases due to their lack of numeric values and often come in the form of text fields written by the consumers (Wolff, R. 2020). The goal of this project is to help in the development of a machine learning model to aid CommonSpirit Health and ServiceNow, hence why this approach using unstructured data was selected. This paper provides a general overview of the process of unstructured data management and explores some existing implementations and their efficacy. It will then discuss our approach to converting unstructured cases into usable data that were used to develop an artificial intelligence model which is estimated to be worth $400,000 and save CommonSpirit Health $1,200,000 in organizational impact.
ContributorsBergsagel, Matteo (Author) / De Waard, Jan (Co-author) / Chavez-Echeagaray, Maria Elena (Thesis director) / Burns, Christopher (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-05
Description
Currently, recommender systems are used extensively to find the right audience with the "right" content over various platforms. Recommendations generated by these systems aim to offer relevant items to users. Different approaches have been suggested to solve this problem mainly by using the rating history of the user or by identifying the preferences of similar users. Most of the existing recommendation systems are formulated in an identical fashion, where a model is trained to capture the underlying preferences of users over different kinds of items. Once it is deployed, the model suggests personalized recommendations precisely, and it is assumed that the preferences of users are perfectly reflected by the historical data. However, such user data might be limited in practice, and the characteristics of users may constantly evolve during their intensive interaction between recommendation systems.
Moreover, most of these recommender systems suffer from the cold-start problems where insufficient data for new users or products results in reduced overall recommendation output. In the current study, we have built a recommender system to recommend movies to users. Biclustering algorithm is used to cluster the users and movies simultaneously at the beginning to generate explainable recommendations, and these biclusters are used to form a gridworld where Q-Learning is used to learn the policy to traverse through the grid. The reward function uses the Jaccard Index, which is a measure of common users between two biclusters. Demographic details of new users are used to generate recommendations that solve the cold-start problem too.
Lastly, the implemented algorithm is examined with a real-world dataset against the widely used recommendation algorithm and the performance for the cold-start cases.
Moreover, most of these recommender systems suffer from the cold-start problems where insufficient data for new users or products results in reduced overall recommendation output. In the current study, we have built a recommender system to recommend movies to users. Biclustering algorithm is used to cluster the users and movies simultaneously at the beginning to generate explainable recommendations, and these biclusters are used to form a gridworld where Q-Learning is used to learn the policy to traverse through the grid. The reward function uses the Jaccard Index, which is a measure of common users between two biclusters. Demographic details of new users are used to generate recommendations that solve the cold-start problem too.
Lastly, the implemented algorithm is examined with a real-world dataset against the widely used recommendation algorithm and the performance for the cold-start cases.
ContributorsSargar, Rushikesh Bapu (Author) / Atkinson, Robert K (Thesis advisor) / Chen, Yinong (Thesis advisor) / Chavez-Echeagaray, Maria Elena (Committee member) / Arizona State University (Publisher)
Created2020