Time series forecasting is the process of analyzing historical data in order to draw conclusions and predict future outcomes. For this project, we explore, compare, and contrast different methods and models of forecasting to determine the advantages and disadvantages of these different systems. We explore, through research papers and code documentation, the commonly used existing methods for working with time series data and present the methods that will be focused on. At regular intervals throughout this project, we will provide presentations covering the results of the different models and the takeaways from working with each method.

The models used for this project have been found from research into what methods are most commonly used for time series forecasting. These models have included ARIMA, Exponential Smoothing, Theta, TBATS, Regression, Recurrent Neural Networks, the Temporal Fusion Transformer, and others. To begin with, these methods have been implemented on a simple dataset tracking car sales every month over a ten year period. Their results have been measured, compared, and logged in an attached PowerPoint presentation, along with brief summaries of how each model works.

Performance of Temporal Fusion Transformer on car sales dataset
Performance of Temporal Fusion Transformer on car sales dataset

These methods will continue to be implemented on more complex, multivariate datasets. Ideally, these models can be tested on complex hospital datasets to provide important data analysis.

PowerPoint:

Time Series Forecasting