Forecast of Consumer Behavior Using Time Series and Ensemble Techniques

Tellaeche Macias, Andres Enrique (2023) Forecast of Consumer Behavior Using Time Series and Ensemble Techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (3MB) | Preview

Abstract

Time series analysis and forecasting is a very important part of machine learning since it has many applications. Time series consists of observations taken in a chronological order. Some of the applications related to time series are the forecasting of the stock price in the stock market, forecasting the demand for certain products, natural language processing, etc. In this research project, we explore the possibility of improving the forecast of the consumer behavior by implementing ensemble techniques. For this reason, we retrieved publicly available data about the sales of alcohol in the United States, particularly in the state of Alabama, and combined them with weather data from the same state. We implemented Autoregressive Integrated Moving Average with Explanatory Variable (ARIMAX), Gated Recurrent Unit (GRU), and Long-Short Term Memory (LSTM) separately and then applied ensemble models using the results obtained by the individual models to improve the final forecast.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Nayak, Prashanth UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HF Commerce > Marketing > Consumer Behaviour Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	08 Jan 2025 16:54
Last Modified:	08 Jan 2025 16:54
URI:	https://norma.ncirl.ie/id/eprint/7283

Actions (login required)

View Item