A model of integration among prediction tools: applied study to road freight transportation

Blois, Henrique Dias; Martins, Ricardo Silveira

doi:10.1016/j.rausp.2016.09.005

Acessibilidade / Reportar erro

Brasil

Revista de Administração (São Paulo)

Español English

Brasil

Español English

sumário « anterior atual seguinte »

Sumário

Marketing • Rev. Adm. (São Paulo) 52 (1) • Jan-Mar 2017 • https://doi.org/10.1016/j.rausp.2016.09.005 copy

A model of integration among prediction tools: applied study to road freight transportation

Um modelo de integração entre ferramentas de previsão: estudo aplicado ao transporte rodoviário de cargas

Un modelo de integración de herramientas de predicción: estudio aplicado al transporte de cargapor carretera

Authorship SCIMAGO INSTITUTIONS RANKINGS

Abstract

This study has developed a scenery analysis model which has integrated decision-making tools on investments: prospective scenarios (Grumbach Method) and systems dynamics (hard modeling), with the innovated multivariate analysis of experts. It was designed through analysis and simulation scenarios and showed which are the most striking events in the study object as well as highlighted the actions could redirect the future of the analyzed system. Moreover, predictions are likely to be developed through the generated scenarios. The model has been validated empirically with road freight transport data from state of Rio Grande do Sul, Brazil. The results showed that the model contributes to the analysis of investment because it identifies probabilities of events that impact on decision making, and identifies priorities for action, reducing uncertainties in the future. Moreover, it allows an interdisciplinary discussion that correlates different areas of knowledge, fundamental when you wish more consistency in creating scenarios.

Keywords
Decisions on investment; Scenarios analysis; Prediction model; Road freight transportation

Method	Mechanisms of employ ed analysis
Godet	-It uses both qualitati ve and quantitati ve variables -It has the clearest detail of the toolin g at all sta ges, co nstit uti ng the most robu st, wi th ste ps to follo w defined -Little flexible -Uses hauliers facts to genera te future sce nari os -On e that do es no t take into a cco unt the mental mode ls of direc tors during the develop men t of the works
GBN	- Generates global scenar ios -It uses only qualitative variables - Fle xible -It uses the analysis"Uncertainty x importance" to generate scenarios. -It is the only one that does not wor k wi th prob ability at any time
Porter	- It drives it s analysis to the industry and adds to the metho d the behav ior of th e competiti on at the en d of the process - Only qualitative varia bles - Fle xible
	- It uses the "unce rtai nty x importa nce" analysis to generate scenarios
Grumbac h	- It uses qualitati ve varia ble s only -Little fle xible -It uses future ha ulier facts to generate sce nari os. -It is the only one usin g the Del phi metho d

Scenarios	Probability	Events
		E.14	E.2	E3	E.4	E.12	E.19	E.6	E.20	E.8	E.9
Scenario 1	24.00%	O	O	O	O	O	O	O	O	O	O
Scenario 2	10.48%	O	O	O	O	N	O	O	O	O	O
Scenario 3	8.58%	O	O	O	O	O	N	O	O	O	O
Scenario 4	4.12%	O	O	O	O	O	O	N	O	O	O
Scenario 5	3.24%	O	O	O	N	O	O	O	O	O	N
Scenario 6	2.88%	O	O	N	O	O	O	O	O	O	O
Scenario 7	2.61%	N	O	O	O	O	O	N	O	O	O
Scenario 8	2.33%	O	O	O	O	N	N	O	O	O	O
Scenario 9	1.89%	O	O	N	O	N	O	O	O	O	O
Scenario 10	1.22%	O	O	O	O	O	N	N	O	O	O

Events
Impact rates
Scenario	Probabilities	E14	E2	E3	E4	E12	E19	E6	E20	E8	E9	1 year	2 years	3 years	4 years	5 years
S.1	24.00%	0	1	1	1	1	1	1	0	0	1	-1.30	-1.39	-1.22	-1.05	-1.33
S.2	10.48%	0	1	1	1	0	1	1	0	0	1	-1.72	-1.82	-1.73	-1.50	-1.78
S.3	8.58%	0	1	1	1	1	0	1	0	0	1	-1.57	-1.66	-1.52	-1.39	-1.62
S.4	4.12%	0	1	1	1	1	1	0	0	0	1	-1.01	-1.10	-0.85	-0.74	-1.01
S.5	3.24%	0	1	1	0	1	1	1	0	0	0	-0.51	-0.46	-0.49	-0.41	-0.49
S.6	2.88%	0	1	0	1	1	1	1	0	0	1	-0.95	-0.73	-0.56	-0.46	-0.65
S.7	2.61%	0	1	1	1	1	1	0	0	0	1	-0.70	-1.10	-0.85	-0.74	-1.01
S.8	2.33%	0	1	1	1	0	0	1	0	0	1	-1.99	-2.09	-2.03	-1.84	-2.07
S.9	1.89%	0	1	0	1	0	1	1	0	0	1	-1.38	-1.46	-1.31	-1.11	-1.37
S.10	1.22%	0	1	1	1	1	0	0	0	0	1	-1.28	-1.37	-1.15	-1.09	-1.30

YEAR	Freight vehicle registration (unit)
2016	25.203
2017	23.957
2018	22.978
2019	22.094
2020	21.060
Variation% between 2016 and 2020	-16.44%

YEAR	Prediction made by SD	Regression of first degree prediction
2016	25.203	29.985
2017	23.957	31.114
2018	22.978	32.242
2019	22.094	33.371
2020	21.060	34.499

Years	Vehicle register	Brazil's GDP growth%
2003	29.709	1.2
2004	24.052	5.7
2005	25.082	3.1
2006	26.026	4
2007	21.639	6

Years	Effective registration	SD prediction	Regression prediction	SD error	Regression error
2008	22.391	25.203	29.985	2.812	7.594
2009	23.111	23.957	31.114	846	8.003
2010	23.962	22.978	32.242	-984	8.280
2011	24.298	22.094	33.371	-2.204	9.073
2012	25.967	21.060	34.499	-4.907	8.532
				2.351	8.296

Departamento de Administração da Faculdade de Economia, Administração e Contabilidade da Universidade de São Paulo Avenida Professor Luciano Gualberto, 908, sala F184, 05508-900 São Paulo / SP Brasil, Tel./Fax 55 11 3818-4002 - São Paulo - SP - Brazil
E-mail: rausp@usp.br

Acompanhe os números deste periódico no seu leitor de RSS

[1] * Corresponding author at: Rua João Lech, 88, 99052 304, Passo Fundo/RS, Brazil. E-mail:blois@upf.br (H.D. Blois).