Development of Welded Line Pipe Price Prediction Model: Comparison Between Linear Regression, ARIMA and ARIMAX Methods at PT Hulu Nasional

DOI

10.2991/978-94-6239-687-6_28How to use a DOI?

Keywords

Procurement; Regression Linear; ARIMA; ARIMAX; Welded Line Pipe; Owner Estimate

Abstract

PT Hulu Nasional, a KKKS that operates under a Cost Recovery scheme, is obligated to formulate a material/service procurement cost estimate (Owner Estimate/OE) that is both valid and reasonable, in accordance with the prevailing market price. The material under scrutiny in this study is Welded Line Pipe. One approach to obtaining a reasonable estimate of the price of welded line pipe is to develop a price prediction model based on historical pipe purchase data and the identification of variables that affect the current pipe price, according to market conditions. In this study, a price prediction model was developed, incorporating three distinct approaches: a causal approach (linear regression), a time series approach (ARIMA), and a combination of causal and time series approaches (ARIMAX). The most suitable model is then determined based on its capacity to predict actual data. Preliminary findings from the linear regression analysis model, which has an adjusted R2 value of 0.7, indicate the presence of variables that exert an influence on the cost of pipes. These variables include the price of crude oil (Brent oil), the exchange rate of the U.S. dollar in relation to the Indonesian rupiah, and the geographical location of material delivery to the KTI Region, which encompasses eastern Indonesia. The ARIMAX (1,1,1) method with two exogenous variables, namely crude oil prices (Brent oil) and the dollar exchange rate, emerged as the optimal model based on the lowest RMSE (109.5), MAPE (2.95%), and MAE (67.35) values when compared to the ARIMA (1,1,1) model and linear regression analysis.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Mutiara Sari Farida Hutabarat
AU  - Nur Aini Masruroh
PY  - 2026
DA  - 2026/05/24
TI  - Development of Welded Line Pipe Price Prediction Model: Comparison Between Linear Regression, ARIMA and ARIMAX Methods at PT Hulu Nasional
BT  - Proceedings of the 8th Mechanical and Industrial Engineering Symposium (MIE 2025)
PB  - Atlantis Press
SP  - 404
EP  - 426
SN  - 2589-4943
UR  - https://doi.org/10.2991/978-94-6239-687-6_28
DO  - 10.2991/978-94-6239-687-6_28
ID  - Hutabarat2026
ER  -