IMPORTANT NOTICE: The date, time, and room assignment of YOUR presentation is SUBJECT TO CHANGE.
Proposal authors can use this tool to see where they have been placed in the program agenda for an Oral or Poster Session.
Scroll down to search by the Submitter or Author Name, by Date/Time, or by Keywords.
Confirm your place in the schedule by following the instructionss that were emailed to you. Each presentation must have a separate paid registration. Contact the ACCI office immedicately by email at admin@consumerinterests.org to report any conflict, all corrections to the details of the presentation (including author names and the order they are listed as this is how it will be in the final program), or if you have any questions. Please be sure to reference the session title(s), date(s), and time(s) when you contact us.
P102 Consumer Saving Behavior: A Multiclassification Approach
Short Description
Using the 2022 Survey of Consumer Finances, this research explores the relationship between savings for emergency, financial, and demographic variables. An essential factor for a family’s financial well-being is the ability to cover unexpected expenses, such as a car or furnace repair, or something even more financially challenging, such as a job loss. (Copeland, 2019). In practice, it is recommended that an individual has at least three months of income in savings in case of emergency. Savings are essential for consumers to pursue long-term financial and overall well-being (Van Praag & Frijters, 2003). To better understand emergency saving behavior, we created an outcome variable that indicates whether the person has at least three months of income in savings. Overall, saving behavior is influenced by many factors. A range of personal and household characteristics, including familial, economic conditions, and financial knowledge, contribute to the likelihood of saving and having financial assets (Babiarz & Robb, 2014; Gjertson, 2016). We use a variety of supervised learning statistical techniques for classification, such as logistic regression, random forest, and support vector machines, to estimate and tune the parameters of our classification model.
Type of presentation
Accepted Poster Presentation