A note on the representative adaptive learning algorithm

We compare forecasts from different adaptive learning algorithms and calibrations applied to US real-time data on inflation and growth. We find that the Least Squares with constant gains adjusted to match (past) survey forecasts provides the best overall performance both in terms of forecasting accuracy and in matching (future) survey forecasts.

MoreLess

Year of publication:	2014
Authors:	Berardi, Michele ; Galimberti, Jaqueson K.
Publisher:	Zurich : ETH Zurich, KOF Swiss Economic Institute
Subject:	expectations \| learning algorithms \| forecasting \| learning-to-forecast \| least squares \| stochastic gradient

More details

Series:	KOF Working Papers ; 356
Type of publication:	Book / Working Paper
Type of publication (narrower categories):	Working Paper
Language:	English
Other identifiers:	10.3929/ethz-a-010131559 [DOI] 783714173 [GVK] hdl:10419/102978 [Handle]
Classification:	C53 - Forecasting and Other Model Applications ; D83 - Search, Learning, Information and Knowledge ; D84 - Expectations; Speculations ; e03 ; E37 - Forecasting and Simulation
Source:	EconStor

Persistent link: https://ebvufind01.dmz1.zbw.eu/10010420579