RT Journal Article
T1 The Yield Curve as a Recession Leading Indicator. An Application for Gradient Boosting and Random Forest
A1 Cadahia Delgado, Pedro
A1 Congregado Ramírez de Aguilera, Emilio
A1 Golpe Moya, Antonio Aníbal
A1 Vides González, José Carlos
AB Most representative decision-tree ensemble methods have been used to examine the variable importance ofTreasury term spreads to predict US economic recessions with a balance of generating rules for US economicrecession detection. A strategy is proposed for training the classifiers with Treasury term spreads data and theresults are compared in order to select the best model for interpretability. We also discuss the use of SHapleyAdditive exPlanations (SHAP) framework to understand US recession forecasts by analyzing feature importance.Consistently with the existing literature we find the most relevant Treasury term spreads for predicting US economicrecession and a methodology for detecting relevant rules for economic recession detection. In this case, the mostrelevant term spread found is 3-month–6-month, which is proposed to be monitored by economic authorities.Finally, the methodology detected rules with high lift on predicting economic recession that can be used by theseentities for this propose. This latter result stands in contrast to a growing body of literature demonstrating thatmachine learning methods are useful for interpretation comparing many alternative algorithms and we discussthe interpretation for our result and propose further research lines aligned with this work.
PB Universidad Internacional de La Rioja
SN 1989-1660
YR 2022
FD 2022
LK http://hdl.handle.net/10272/21216
UL http://hdl.handle.net/10272/21216
LA eng
NO Cadahia Delgado, P., Congregado, E., Golpe, A. A., & Vides, J. C. (2022). The Yield Curve as a Recession Leading Indicator. An Application for Gradient Boosting and Random Forest. In International Journal of Interactive Multimedia and Artificial Intelligence (Vol. 7, Issue 3, p. 7). Universidad Internacional de La Rioja. https://doi.org/10.9781/ijimai.2022.02.006
DS Repositorio Institucional de la Universidad de Huelva
RD 31 may 2026