Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM: COVID-19 Case Study

M. A.Machaca Arceda; P. C.Laguna Laura; V. E.Machaca Arceda

doi:10.1007/978-3-030-63089-8_36

Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM: COVID-19 Case Study

M. A.Machaca Arceda, P. C.Laguna Laura, V. E.Machaca Arceda

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this work, we present an analysis of time series of COVID-19 confirmed cases with Multiplicative Trend Exponential Smoothing (MTES) and Long Short-Term Memory (LSTM). We evaluated the results utilizing COVID-19 confirmed cases data from countries with higher indices as the United States (US), Italy, Spain, and other countries that presumably have stopped the virus, like China, New Zealand, and Australia. Additionally, we used data from a Git repository which is daily updated, when we did the experiments we used data up to April 28th. We used 80% of data to train both models and then, we computed the Root Mean Square Error (RMSE) of test ground true data and predictions. In our experiments, MTES outperformed LSTM, we believe it is caused by a lack of historical data and the particular behavior of each country. To conclude, we performed a forecasting of new COVID-19 confirmed cases using MTES with 10 days ahead.

Original language	English
Title of host publication	Proceedings of the Future Technologies Conference, FTC 2020, Volume 2
Editors	Kohei Arai, Supriya Kapoor, Rahul Bhatia
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	568-582
Number of pages	15
ISBN (Print)	9783030630881
DOIs	https://doi.org/10.1007/978-3-030-63089-8_36
State	Published - 2021
Externally published	Yes
Event	Future Technologies Conference, FTC 2020 - San Francisco, United States Duration: 5 Nov 2020 → 6 Nov 2020

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1289
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	Future Technologies Conference, FTC 2020
Country/Territory	United States
City	San Francisco
Period	5/11/20 → 6/11/20

Bibliographical note

Publisher Copyright:
© 2021, Springer Nature Switzerland AG.

Keywords

COVID-19
Forecasting
LSTM
MTES
Time series

Access to Document

10.1007/978-3-030-63089-8_36

Cite this

Arceda, M. A. M., Laura, P. C. L., & Arceda, V. E. M. (2021). Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM: COVID-19 Case Study. In K. Arai, S. Kapoor, & R. Bhatia (Eds.), Proceedings of the Future Technologies Conference, FTC 2020, Volume 2 (pp. 568-582). (Advances in Intelligent Systems and Computing; Vol. 1289). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-63089-8_36

Arceda, M. A.Machaca ; Laura, P. C.Laguna ; Arceda, V. E.Machaca. / Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM : COVID-19 Case Study. Proceedings of the Future Technologies Conference, FTC 2020, Volume 2. editor / Kohei Arai ; Supriya Kapoor ; Rahul Bhatia. Springer Science and Business Media Deutschland GmbH, 2021. pp. 568-582 (Advances in Intelligent Systems and Computing).

@inproceedings{dc85a45f411546e49b9466bf9a4f59ff,

title = "Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM: COVID-19 Case Study",

abstract = "In this work, we present an analysis of time series of COVID-19 confirmed cases with Multiplicative Trend Exponential Smoothing (MTES) and Long Short-Term Memory (LSTM). We evaluated the results utilizing COVID-19 confirmed cases data from countries with higher indices as the United States (US), Italy, Spain, and other countries that presumably have stopped the virus, like China, New Zealand, and Australia. Additionally, we used data from a Git repository which is daily updated, when we did the experiments we used data up to April 28th. We used 80% of data to train both models and then, we computed the Root Mean Square Error (RMSE) of test ground true data and predictions. In our experiments, MTES outperformed LSTM, we believe it is caused by a lack of historical data and the particular behavior of each country. To conclude, we performed a forecasting of new COVID-19 confirmed cases using MTES with 10 days ahead.",

keywords = "COVID-19, Forecasting, LSTM, MTES, Time series",

author = "Arceda, {M. A.Machaca} and Laura, {P. C.Laguna} and Arceda, {V. E.Machaca}",

note = "Publisher Copyright: {\textcopyright} 2021, Springer Nature Switzerland AG.; null ; Conference date: 05-11-2020 Through 06-11-2020",

year = "2021",

doi = "10.1007/978-3-030-63089-8_36",

language = "Ingl{\'e}s",

isbn = "9783030630881",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "568--582",

editor = "Kohei Arai and Supriya Kapoor and Rahul Bhatia",

booktitle = "Proceedings of the Future Technologies Conference, FTC 2020, Volume 2",

address = "Alemania",

}

Arceda, MAM, Laura, PCL & Arceda, VEM 2021, Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM: COVID-19 Case Study. in K Arai, S Kapoor & R Bhatia (eds), Proceedings of the Future Technologies Conference, FTC 2020, Volume 2. Advances in Intelligent Systems and Computing, vol. 1289, Springer Science and Business Media Deutschland GmbH, pp. 568-582, Future Technologies Conference, FTC 2020, San Francisco, United States, 5/11/20. https://doi.org/10.1007/978-3-030-63089-8_36

Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM : COVID-19 Case Study. / Arceda, M. A.Machaca; Laura, P. C.Laguna; Arceda, V. E.Machaca.

Proceedings of the Future Technologies Conference, FTC 2020, Volume 2. ed. / Kohei Arai; Supriya Kapoor; Rahul Bhatia. Springer Science and Business Media Deutschland GmbH, 2021. p. 568-582 (Advances in Intelligent Systems and Computing; Vol. 1289).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM

AU - Arceda, M. A.Machaca

AU - Laura, P. C.Laguna

AU - Arceda, V. E.Machaca

PY - 2021

Y1 - 2021

N2 - In this work, we present an analysis of time series of COVID-19 confirmed cases with Multiplicative Trend Exponential Smoothing (MTES) and Long Short-Term Memory (LSTM). We evaluated the results utilizing COVID-19 confirmed cases data from countries with higher indices as the United States (US), Italy, Spain, and other countries that presumably have stopped the virus, like China, New Zealand, and Australia. Additionally, we used data from a Git repository which is daily updated, when we did the experiments we used data up to April 28th. We used 80% of data to train both models and then, we computed the Root Mean Square Error (RMSE) of test ground true data and predictions. In our experiments, MTES outperformed LSTM, we believe it is caused by a lack of historical data and the particular behavior of each country. To conclude, we performed a forecasting of new COVID-19 confirmed cases using MTES with 10 days ahead.

AB - In this work, we present an analysis of time series of COVID-19 confirmed cases with Multiplicative Trend Exponential Smoothing (MTES) and Long Short-Term Memory (LSTM). We evaluated the results utilizing COVID-19 confirmed cases data from countries with higher indices as the United States (US), Italy, Spain, and other countries that presumably have stopped the virus, like China, New Zealand, and Australia. Additionally, we used data from a Git repository which is daily updated, when we did the experiments we used data up to April 28th. We used 80% of data to train both models and then, we computed the Root Mean Square Error (RMSE) of test ground true data and predictions. In our experiments, MTES outperformed LSTM, we believe it is caused by a lack of historical data and the particular behavior of each country. To conclude, we performed a forecasting of new COVID-19 confirmed cases using MTES with 10 days ahead.

KW - COVID-19

KW - Forecasting

KW - LSTM

KW - MTES

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=85096462418&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-63089-8_36

DO - 10.1007/978-3-030-63089-8_36

M3 - Contribución a la conferencia

AN - SCOPUS:85096462418

SN - 9783030630881

T3 - Advances in Intelligent Systems and Computing

SP - 568

EP - 582

BT - Proceedings of the Future Technologies Conference, FTC 2020, Volume 2

A2 - Arai, Kohei

A2 - Kapoor, Supriya

A2 - Bhatia, Rahul

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 5 November 2020 through 6 November 2020

ER -

Arceda MAM, Laura PCL, Arceda VEM. Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM: COVID-19 Case Study. In Arai K, Kapoor S, Bhatia R, editors, Proceedings of the Future Technologies Conference, FTC 2020, Volume 2. Springer Science and Business Media Deutschland GmbH. 2021. p. 568-582. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-030-63089-8_36

Forecasting Time Series with Multiplicative Trend Exponential Smoothing and LSTM: COVID-19 Case Study

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this