Including news data in forecasting macro economic performance of China

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

Standard

Including news data in forecasting macro economic performance of China. / Lunde, Asger; Torkar, Miha.

I: Computational Management Science, Bind 17, Nr. 4, 12.2020, s. 585-611.

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

Vancouver

Lunde A, Torkar M. Including news data in forecasting macro economic performance of China. Computational Management Science. 2020 dec.;17(4):585-611. doi: 10.1007/s10287-020-00382-5

Author

Lunde, Asger ; Torkar, Miha. / Including news data in forecasting macro economic performance of China. I: Computational Management Science. 2020 ; Bind 17, Nr. 4. s. 585-611.

Bibtex

@article{31b10f4330f9462bb9fe66f552d8a03b,

title = "Including news data in forecasting macro economic performance of China",

abstract = "In this work we predict changes in the Gross Domestic Product (GDP) of China using dynamic factor models. We report results of 3- and 6-months ahead forecasts, where we use 124 predictors from various sources and dates ranging from 2000 through 2017. Our analysis includes China specific macroeconomic time series data and a large number of predictor variables. We follow the latest state of the art, as outlined by, Stock and Watson (in: Handbook of macroeconomics vol 2, Elsevier, pp 415–525, 2016) who use principal component analysis (PCA) to reduce number of variables and apply dynamic factor model (DFM) to make predictions. The results suggest that including news sentiment significantly improves forecasts and this approach outperforms univariate autoregression. The contributions of this paper are two fold, namely, the use of news to improve forecasts and superior forecast of China{\textquoteright}s GDP.",

keywords = "Factor models, Macroeconomics, News, Principal component analysis, Sentiment",

author = "Asger Lunde and Miha Torkar",

note = "Publisher Copyright: {\textcopyright} 2020, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.",

year = "2020",

month = dec,

doi = "10.1007/s10287-020-00382-5",

language = "English",

volume = "17",

pages = "585--611",

journal = "Computational Management Science",

issn = "1619-697X",

publisher = "Springer",

number = "4",

}

RIS

TY - JOUR

T1 - Including news data in forecasting macro economic performance of China

AU - Lunde, Asger

AU - Torkar, Miha

PY - 2020/12

Y1 - 2020/12

N2 - In this work we predict changes in the Gross Domestic Product (GDP) of China using dynamic factor models. We report results of 3- and 6-months ahead forecasts, where we use 124 predictors from various sources and dates ranging from 2000 through 2017. Our analysis includes China specific macroeconomic time series data and a large number of predictor variables. We follow the latest state of the art, as outlined by, Stock and Watson (in: Handbook of macroeconomics vol 2, Elsevier, pp 415–525, 2016) who use principal component analysis (PCA) to reduce number of variables and apply dynamic factor model (DFM) to make predictions. The results suggest that including news sentiment significantly improves forecasts and this approach outperforms univariate autoregression. The contributions of this paper are two fold, namely, the use of news to improve forecasts and superior forecast of China’s GDP.

AB - In this work we predict changes in the Gross Domestic Product (GDP) of China using dynamic factor models. We report results of 3- and 6-months ahead forecasts, where we use 124 predictors from various sources and dates ranging from 2000 through 2017. Our analysis includes China specific macroeconomic time series data and a large number of predictor variables. We follow the latest state of the art, as outlined by, Stock and Watson (in: Handbook of macroeconomics vol 2, Elsevier, pp 415–525, 2016) who use principal component analysis (PCA) to reduce number of variables and apply dynamic factor model (DFM) to make predictions. The results suggest that including news sentiment significantly improves forecasts and this approach outperforms univariate autoregression. The contributions of this paper are two fold, namely, the use of news to improve forecasts and superior forecast of China’s GDP.

KW - Factor models

KW - Macroeconomics

KW - News

KW - Principal component analysis

KW - Sentiment

UR - http://www.scopus.com/inward/record.url?scp=85097986145&partnerID=8YFLogxK

U2 - 10.1007/s10287-020-00382-5

DO - 10.1007/s10287-020-00382-5

M3 - Journal article

AN - SCOPUS:85097986145

VL - 17

SP - 585

EP - 611

JO - Computational Management Science

JF - Computational Management Science

SN - 1619-697X

IS - 4

ER -

Department of Economics and Business Economics

CREATES

CREATES