Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications

Abstract. In this research, we consider monthly series from the M4 competition to study the relative performance of top-down and bottom-up strategies by means of implementing forecast automation of state space and ARIMA models. For the bottomup strategy, the forecast for each series is developed ind...

Full description

Autores:
Soto-Ferrari, Milton
Chams-Anturi, Odette
Escorcia-Caballero, Juan P.
Hussain, Namra
Khan, Muhammad
Tipo de recurso:
http://purl.org/coar/resource_type/c_816b
Fecha de publicación:
2019
Institución:
Corporación Universidad de la Costa
Repositorio:
REDICUC - Repositorio CUC
Idioma:
eng
OAI Identifier:
oai:repositorio.cuc.edu.co:11323/5809
Acceso en línea:
https://hdl.handle.net/11323/5809
https://repositorio.cuc.edu.co/
Palabra clave:
Top-down
Bottom-up
Forecast automation
Forecast performance
State space models
ARIMA
Rights
openAccess
License
CC0 1.0 Universal
id RCUC2_6e7ee92ffe2a41f40a0efa4e92df9dc7
oai_identifier_str oai:repositorio.cuc.edu.co:11323/5809
network_acronym_str RCUC2
network_name_str REDICUC - Repositorio CUC
repository_id_str
dc.title.spa.fl_str_mv Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications
title Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications
spellingShingle Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications
Top-down
Bottom-up
Forecast automation
Forecast performance
State space models
ARIMA
title_short Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications
title_full Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications
title_fullStr Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications
title_full_unstemmed Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications
title_sort Evaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applications
dc.creator.fl_str_mv Soto-Ferrari, Milton
Chams-Anturi, Odette
Escorcia-Caballero, Juan P.
Hussain, Namra
Khan, Muhammad
dc.contributor.author.spa.fl_str_mv Soto-Ferrari, Milton
Chams-Anturi, Odette
Escorcia-Caballero, Juan P.
Hussain, Namra
Khan, Muhammad
dc.subject.spa.fl_str_mv Top-down
Bottom-up
Forecast automation
Forecast performance
State space models
ARIMA
topic Top-down
Bottom-up
Forecast automation
Forecast performance
State space models
ARIMA
description Abstract. In this research, we consider monthly series from the M4 competition to study the relative performance of top-down and bottom-up strategies by means of implementing forecast automation of state space and ARIMA models. For the bottomup strategy, the forecast for each series is developed individually and then these are combined to produce a cumulative forecast of the aggregated series. For the top-down strategy, the series or components values are first combined and then a single forecast is determined for the aggregated series. Based on our implementation, state space models showed a higher forecast performance when a top-down strategy is applied. ARIMA models had a higher forecast performance for the bottom-up strategy. For state space models the top-down strategy reduced the overall error significantly. ARIMA models showed to be more accurate when forecasts are first determined individually. As part of the development we also proposed an approach to improve the forecasting procedure of aggregation strategies.
publishDate 2019
dc.date.issued.none.fl_str_mv 2019-09-20
dc.date.accessioned.none.fl_str_mv 2020-01-13T19:11:46Z
dc.date.available.none.fl_str_mv 2020-01-13T19:11:46Z
dc.type.spa.fl_str_mv Pre-Publicación
dc.type.coar.spa.fl_str_mv http://purl.org/coar/resource_type/c_816b
dc.type.content.spa.fl_str_mv Text
dc.type.driver.spa.fl_str_mv info:eu-repo/semantics/preprint
dc.type.redcol.spa.fl_str_mv http://purl.org/redcol/resource_type/ARTOTR
dc.type.version.spa.fl_str_mv info:eu-repo/semantics/acceptedVersion
format http://purl.org/coar/resource_type/c_816b
status_str acceptedVersion
dc.identifier.uri.spa.fl_str_mv https://hdl.handle.net/11323/5809
dc.identifier.instname.spa.fl_str_mv Corporación Universidad de la Costa
dc.identifier.reponame.spa.fl_str_mv REDICUC - Repositorio CUC
dc.identifier.repourl.spa.fl_str_mv https://repositorio.cuc.edu.co/
url https://hdl.handle.net/11323/5809
https://repositorio.cuc.edu.co/
identifier_str_mv Corporación Universidad de la Costa
REDICUC - Repositorio CUC
dc.language.iso.none.fl_str_mv eng
language eng
dc.relation.references.spa.fl_str_mv 1. Mentzer, J., Bienstock, C.: Sales Forecasting Management: Understanding the Techniques. Syst. Manag. Sales Forecast. Process. Sage Publ. (1998).
2. Hyndman, R., Koehler, A., Snyder, R., Grose, S.: A state space framework for automatic forecasting using exponential smoothing methods. Int. J. Forecast. 18, 439–454 (2002).
3. Fildes, R., Petropoulos, F.: Simple versus complex selection rules for forecasting many time series. J. Bus. Res. 68, 1692–1701 (2015).
4. Hendry, D., Hubrich, K.: Combining disaggregate forecasts or combining disaggregate information to forecast an aggregate. J. Bus. Econ. Stat. 29, 216– 227 (2011).
5. Widiarta, H., Viswanathan, S.: Forecasting family demand with autoregressive item-level demands: Evaluation of top-downand bottom-up forecasting strategies. Work. Pap. (2005).
6. McLeavey, D., Narasimhan, S.: Production Planning and Inventory Control. Allyn Bacon, Inc., Bost. (1985).
7. Lutkepohl, H.: Forecasting With VARMA Processes. Handb. Eco nomic Forecast. eds. G. Elliott, C. W. J. Granger, A. Timmermann, Amsterdam, Netherlands Elsevier. (2006).
8. Seifert, M., Siemsen, E., Hadida, A., Eisingerich, A.: Effective judgmental forecasting in the context of fashion products. J. Oper. Manag. 36, 33–45 (2015).
9. Nenova, Z., May, J.: Determining an optimal hierarchical forecasting model based on the characteristics of the dataset: technical note. J. Oper. Manag. 44, 62–88 (2016).
10. Van der Laan, E., Van Dalen, J., Rohrmoser, M., Simpson, R.: Demand forecasting and order planning for humanitarian logistics: an empirical assessment. J. Oper. Manag. 45, 114–122 (2016).
11. Zotteri, G., Kalchschmidt, M., Caniato, F.: The impact of aggregation level on forecasting performance. Int. J. Prod. Econ. 93, 479–491 (2005).
12. Theil, H.: Linear Aggregation of Economic Relations. North-holl. Publ. Company, Amsterdam. (1954).
13. Y., G., Griliches, Z.: Is Aggregation Necessarily Bad? Rev. Econ. Stat. 42, 1– 13 (1960).
14. Schwarzkoph, A., Tersine, R., Morris, J.: Topdown versus bottom-up forecasting strategies. Int. J. Prod. Res. 26, 1833–1843 (1988).
15. Oller, L.: Aggregating problems when forecasting industrial production using business survey data. Discuss. Pap. No. 20, Minist. ofFinance, Econ. Dep. Helsinky. (1989).
16. Ilmakunnas, P.: Aggregation vs. disaggregation in forecasting construction activity. Barker, T.S., Pesaran, H. (Eds.), Disaggregation Econom. Model. Routledge, London. 73–86 (1990).
17. Kahn, K.: Revisiting top-down versus bottom-up forecasting. J. Bus. Forecast. 14–19 (1998).
18. Lapide, L.: New developments in business forecasting. J. Ofbus. Forecast. 28–29 (1998).
19. Orcutt, G., Watts, H., Edwards, J.: Data aggregation and information loss. Am. Econ. Rev. 58, 773–787 (1968).
20. Zellner, A., Tobias, J.: A note on aggregation, disaggregation and forecasting performance. J. Forecast. 19, 457–469 (2000).
21. Weatherford, L., Kimes, S., Scott, D.: Forecasting for hotel revenue management: Testing aggregation against disaggregation. Cornell Hotel Restaur. Adm. Q. 53–64 (2001).
22. Makridakis, S., Hibon, M.: The M3-competition: Results, conclusions and implications. Int. J. Forecast. 16, 451–476 (2000).
23. Chu, C., Zhang, P.: A comparative study of linear and nonlinear models for aggregate retail sales forecasting. Int. J. Prod. Econ. 86, 217–231 (2003).
dc.rights.spa.fl_str_mv CC0 1.0 Universal
dc.rights.uri.spa.fl_str_mv http://creativecommons.org/publicdomain/zero/1.0/
dc.rights.accessrights.spa.fl_str_mv info:eu-repo/semantics/openAccess
dc.rights.coar.spa.fl_str_mv http://purl.org/coar/access_right/c_abf2
rights_invalid_str_mv CC0 1.0 Universal
http://creativecommons.org/publicdomain/zero/1.0/
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.publisher.spa.fl_str_mv Universidad de la Costa
institution Corporación Universidad de la Costa
bitstream.url.fl_str_mv https://repositorio.cuc.edu.co/bitstreams/67f3aa1c-c9a3-43a7-8249-b6aced0288ec/download
https://repositorio.cuc.edu.co/bitstreams/8169b2f2-b4d0-497a-86be-2eb2db249b33/download
https://repositorio.cuc.edu.co/bitstreams/a405fcd3-7325-43b1-907b-535aed501388/download
https://repositorio.cuc.edu.co/bitstreams/63018953-3612-4c74-8b85-b40880077010/download
https://repositorio.cuc.edu.co/bitstreams/cc547f0f-01e1-4a66-b65b-911237a89efd/download
bitstream.checksum.fl_str_mv 64044aec4f4af25cd031fb2f638e5825
42fd4ad1e89814f5e4a476b409eb708c
8a4605be74aa9ea9d79846c1fba20a33
bad6c8ea2d650d071f59678790d6b9c7
1f73577cc60e331bc25f924553942fc6
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
MD5
MD5
MD5
repository.name.fl_str_mv Repositorio de la Universidad de la Costa CUC
repository.mail.fl_str_mv repdigital@cuc.edu.co
_version_ 1811760755215695872
spelling Soto-Ferrari, MiltonChams-Anturi, OdetteEscorcia-Caballero, Juan P.Hussain, NamraKhan, Muhammad2020-01-13T19:11:46Z2020-01-13T19:11:46Z2019-09-20https://hdl.handle.net/11323/5809Corporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.co/Abstract. In this research, we consider monthly series from the M4 competition to study the relative performance of top-down and bottom-up strategies by means of implementing forecast automation of state space and ARIMA models. For the bottomup strategy, the forecast for each series is developed individually and then these are combined to produce a cumulative forecast of the aggregated series. For the top-down strategy, the series or components values are first combined and then a single forecast is determined for the aggregated series. Based on our implementation, state space models showed a higher forecast performance when a top-down strategy is applied. ARIMA models had a higher forecast performance for the bottom-up strategy. For state space models the top-down strategy reduced the overall error significantly. ARIMA models showed to be more accurate when forecasts are first determined individually. As part of the development we also proposed an approach to improve the forecasting procedure of aggregation strategies.Soto-Ferrari, Milton-will be generated-orcid-0000-0002-0255-968X-600Chams-Anturi, Odette-will be generated-orcid-0000-0002-8353-7326-600Escorcia-Caballero, Juan P.-will be generated-orcid-0000-0001-8425-0266-600Hussain, NamraKhan, MuhammadengUniversidad de la CostaCC0 1.0 Universalhttp://creativecommons.org/publicdomain/zero/1.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Top-downBottom-upForecast automationForecast performanceState space modelsARIMAEvaluation of bottom-up and top-down strategies for aggregated forecasts: state space models and arima applicationsPre-Publicaciónhttp://purl.org/coar/resource_type/c_816bTextinfo:eu-repo/semantics/preprinthttp://purl.org/redcol/resource_type/ARTOTRinfo:eu-repo/semantics/acceptedVersion1. Mentzer, J., Bienstock, C.: Sales Forecasting Management: Understanding the Techniques. Syst. Manag. Sales Forecast. Process. Sage Publ. (1998).2. Hyndman, R., Koehler, A., Snyder, R., Grose, S.: A state space framework for automatic forecasting using exponential smoothing methods. Int. J. Forecast. 18, 439–454 (2002).3. Fildes, R., Petropoulos, F.: Simple versus complex selection rules for forecasting many time series. J. Bus. Res. 68, 1692–1701 (2015).4. Hendry, D., Hubrich, K.: Combining disaggregate forecasts or combining disaggregate information to forecast an aggregate. J. Bus. Econ. Stat. 29, 216– 227 (2011).5. Widiarta, H., Viswanathan, S.: Forecasting family demand with autoregressive item-level demands: Evaluation of top-downand bottom-up forecasting strategies. Work. Pap. (2005).6. McLeavey, D., Narasimhan, S.: Production Planning and Inventory Control. Allyn Bacon, Inc., Bost. (1985).7. Lutkepohl, H.: Forecasting With VARMA Processes. Handb. Eco nomic Forecast. eds. G. Elliott, C. W. J. Granger, A. Timmermann, Amsterdam, Netherlands Elsevier. (2006).8. Seifert, M., Siemsen, E., Hadida, A., Eisingerich, A.: Effective judgmental forecasting in the context of fashion products. J. Oper. Manag. 36, 33–45 (2015).9. Nenova, Z., May, J.: Determining an optimal hierarchical forecasting model based on the characteristics of the dataset: technical note. J. Oper. Manag. 44, 62–88 (2016).10. Van der Laan, E., Van Dalen, J., Rohrmoser, M., Simpson, R.: Demand forecasting and order planning for humanitarian logistics: an empirical assessment. J. Oper. Manag. 45, 114–122 (2016).11. Zotteri, G., Kalchschmidt, M., Caniato, F.: The impact of aggregation level on forecasting performance. Int. J. Prod. Econ. 93, 479–491 (2005).12. Theil, H.: Linear Aggregation of Economic Relations. North-holl. Publ. Company, Amsterdam. (1954).13. Y., G., Griliches, Z.: Is Aggregation Necessarily Bad? Rev. Econ. Stat. 42, 1– 13 (1960).14. Schwarzkoph, A., Tersine, R., Morris, J.: Topdown versus bottom-up forecasting strategies. Int. J. Prod. Res. 26, 1833–1843 (1988).15. Oller, L.: Aggregating problems when forecasting industrial production using business survey data. Discuss. Pap. No. 20, Minist. ofFinance, Econ. Dep. Helsinky. (1989).16. Ilmakunnas, P.: Aggregation vs. disaggregation in forecasting construction activity. Barker, T.S., Pesaran, H. (Eds.), Disaggregation Econom. Model. Routledge, London. 73–86 (1990).17. Kahn, K.: Revisiting top-down versus bottom-up forecasting. J. Bus. Forecast. 14–19 (1998).18. Lapide, L.: New developments in business forecasting. J. Ofbus. Forecast. 28–29 (1998).19. Orcutt, G., Watts, H., Edwards, J.: Data aggregation and information loss. Am. Econ. Rev. 58, 773–787 (1968).20. Zellner, A., Tobias, J.: A note on aggregation, disaggregation and forecasting performance. J. Forecast. 19, 457–469 (2000).21. Weatherford, L., Kimes, S., Scott, D.: Forecasting for hotel revenue management: Testing aggregation against disaggregation. Cornell Hotel Restaur. Adm. Q. 53–64 (2001).22. Makridakis, S., Hibon, M.: The M3-competition: Results, conclusions and implications. Int. J. Forecast. 16, 451–476 (2000).23. Chu, C., Zhang, P.: A comparative study of linear and nonlinear models for aggregate retail sales forecasting. Int. J. Prod. Econ. 86, 217–231 (2003).PublicationORIGINALEvaluation of Bottom-up and Top-down Strategies for aggregated foreasts.pdfEvaluation of Bottom-up and Top-down Strategies for aggregated foreasts.pdfapplication/pdf1373206https://repositorio.cuc.edu.co/bitstreams/67f3aa1c-c9a3-43a7-8249-b6aced0288ec/download64044aec4f4af25cd031fb2f638e5825MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8701https://repositorio.cuc.edu.co/bitstreams/8169b2f2-b4d0-497a-86be-2eb2db249b33/download42fd4ad1e89814f5e4a476b409eb708cMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-81748https://repositorio.cuc.edu.co/bitstreams/a405fcd3-7325-43b1-907b-535aed501388/download8a4605be74aa9ea9d79846c1fba20a33MD53THUMBNAILEvaluation of Bottom-up and Top-down Strategies for aggregated foreasts.pdf.jpgEvaluation of Bottom-up and Top-down Strategies for aggregated foreasts.pdf.jpgimage/jpeg45205https://repositorio.cuc.edu.co/bitstreams/63018953-3612-4c74-8b85-b40880077010/downloadbad6c8ea2d650d071f59678790d6b9c7MD55TEXTEvaluation of Bottom-up and Top-down Strategies for aggregated foreasts.pdf.txtEvaluation of Bottom-up and Top-down Strategies for aggregated foreasts.pdf.txttext/plain37796https://repositorio.cuc.edu.co/bitstreams/cc547f0f-01e1-4a66-b65b-911237a89efd/download1f73577cc60e331bc25f924553942fc6MD5611323/5809oai:repositorio.cuc.edu.co:11323/58092024-09-17 10:59:41.647http://creativecommons.org/publicdomain/zero/1.0/CC0 1.0 Universalopen.accesshttps://repositorio.cuc.edu.coRepositorio de la Universidad de la Costa CUCrepdigital@cuc.edu.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