ARIMA and SVM forecasting in the US paper waste

Pei Hsuan Lee

doi:10.1117/12.2639463

17 May 2022 ARIMA and SVM forecasting in the US paper waste

Pei Hsuan Lee

Proceedings Volume 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022); 122595W (2022) https://doi.org/10.1117/12.2639463
Event: 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), 2022, Kunming, China

Abstract

Technology makes the lifestyle more convenient, whereas convenience could contribute to more severe waste problems. Accordingly, waste organisations can rely on adequate and accurate waste generation forecasting models to effectively solve ecological issues. This study aims to compare the forecasting methods between ARIMA and SVM models in the annual US paper/paper board waste from 1960 to 2018 based upon the time series forecasting in household paper/paper board waste generation in the United States. This research introduces the utilisation of paper and paper board waste forecasting in disposal management and general statistical methods application, and analyses the time series prediction models and detailed processes between ARIMA and SVM. The analysis in ARIMA notices the data transformation and in SVM mentions the multicollinearity issues. Besides, this study discusses and compares the performance of two approaches by measuring the accuracy with MAPE, MAE, and RMSE; the conventional statistical method, ARIMA, has lower errors than SVM. The analysis, along with the conventional statistical and machine learning approaches, shows that ARIMA is highly suggested. Finally, the suggestions in related US household paper/cardboard waste issues are put forward.

Citation Download Citation

Pei Hsuan Lee "ARIMA and SVM forecasting in the US paper waste", Proc. SPIE 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), 122595W (17 May 2022); https://doi.org/10.1117/12.2639463

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available