Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
- Publication Type
Articles 1 - 2 of 2
Full-Text Articles in Macroeconomics
Essays On Convex Weighting For Global Vector Autoregressive Models, Garrison Leach
Essays On Convex Weighting For Global Vector Autoregressive Models, Garrison Leach
Economics Theses and Dissertations
This dissertation focuses on studying the impact that weighting schemes can have on forecasting performance and dynamic analysis in global vector autoregressive (GVAR) models. The first chapter discusses an existing gap in the literature regarding weighting scheme choice and develops a simple, yet powerful method for defining richer spatial linkages in a way that doesn’t sacrifice economic context. The new technique called convex weighting, extends the set of available options for defining spatial linkages in models that handle the curse of dimensionality via compression and offers a justifiable approach to alleviating uncertainty. The second and third chapters apply the newly …
Improvements To Consumption Prediction: Machine Learning Methods And Novel Features, Ian Kinskey, Glenn Oswald, Charles Mccann, Travis Finch, Anthony Tanaydin
Improvements To Consumption Prediction: Machine Learning Methods And Novel Features, Ian Kinskey, Glenn Oswald, Charles Mccann, Travis Finch, Anthony Tanaydin
SMU Data Science Review
Current models for predicting personal consumption expenditures (PCE) employ statistical techniques and rely upon traditional economic features. We compare vector autoregression and random forest regression models using traditional economic features as inputs to predict PCE. Additionally, we develop novel features derived from the earnings call transcripts of publicly traded U.S. companies using natural language processing (NLP) techniques. These new features reduce the mean square error (MSE) of the vector autoregression model by 7% and the random forest model by 23%. We find the random forest models outperformed the vector autoregression models, with a MSE reduction of 68%. We conclude the …