APPLYING MULTILAYER PERCEPTRON AND DATA FILTERING FOR PRELIMINARY SECOND-HAND SHIP PRICE ESTIMATION

Authors

DOI:

https://doi.org/10.26408/139.04

Keywords:

MLP, WEKA, bulk carrier, price estimation

Abstract

This research investigates the use of a Multilayer Perceptron (MLP) neural network combined with Z-score filtering for preliminary estimation of second-hand ship prices of bulk carriers and tankers. A simplified dataset containing only deadweight tonnage (DWT) and sale price was preprocessed to remove outliers and improve normality. A single MLP architecture with an automatic hidden layer configuration was implemented in the DataMelt environment using WEKA through Jython scripting. Model evaluation showed moderate predictive performance (correlation ≈ 0.50; R² ≈ 0.25), indicating that even minimal input features can provide rough cost estimates for early-stage procurement decisions. The findings confirm the potential of neural networks for maritime price forecasting while emphasizing the need for richer datasets to improve accuracy.

References

Azhar, A. (2021). Method for estimating price of second hand ship with multi method. IOP Conf. Ser.: Mater. Sci. Eng. 1052, 012011. https://doi.org/10.1088/1757-899X/1052/1/012011

Bal, E. T., Akan, E., & Gencer, H. (2025). A Novel approach to ship valuation prediction: An application to the supramax and ultramax secondhand markets. PLoS One, 20, e0319073. https://doi.org/10.1371/journal.pone.0319073

Beckham, C., Hall, M., & Frank, E. (2016). WekaPyScript: Classification, regression, and filter schemes for WEKA implemented in Python. JORS 4, 33. https://doi.org/10.5334/jors.108

Cassales, G. W., Liu, J. J., & Bifet, A. (2025). Accelerated WEKA: GPU machine learning with WEKA Workbench. Neurocomputing 646, 130432. https://doi.org/10.1016/j.neucom.2025.130432

Chekanov, S. V. (2010). Scientific data analysis using Jython scripting and Java, advanced information and knowledge processing. Springer London. https://doi.org/10.1007/978-1-84996-287-2_1

Chekanov, S. V. (2016). Numeric computation and statistical data analysis on the Java Platform. 1st ed. Advanced Information and Knowledge Processing. Springer. https://doi.org/10.1007/978-3-319-28531-3

Chekanov, S. V. (2024). The designed world of information: Unveiling the incredible realm beyond. 2nd ed. Sergei V. Chekanov.

Frank, E., Hall, M., Holmes, G., Kirkby, R., Pfahringer, B., Witten, I. H., & Trigg, L. (2009). WEKA – A machine learning workbench for data mining. In O. Maimon, L. Rokach (Eds.), Data mining and knowledge discovery handbook (pp. 1269-1277). Springer US. https://doi.org/10.1007/978-0-387-09823-4_66

Gresia, Y., Anggraini, L. D., & Putri, A. U. (2023). Analysis of the determination of product selling price using the cost plus pricing method (Case study at UD Homebake Palembang). IJCSE, 4, 100-104. https://doi.org/10.47747/ijcse.v4i3.1384

Haykin, S. S. (2009). Neural networks and learning machines. 3. ed. Prentice-Hall.

Hochkamp, F., Rabe, M., Kersten, W., Jahn, C., Blecker, T., & Ringle, C. M. (2022). Outlier detection in data mining: Exclusion of errors or loss of information? Hamburg International Conference of Logistics (HICL), 33, 91-117. https://doi.org/10.15480/882.4689

Koç Ustali, N., Merdivenci, F., & Aydın, S. Z. (2024). Evaluation of factors affecting price in second hand ship market: Turkey application with the SWARA method. Maritime Policy & Management 51, 981-994. https://doi.org/10.1080/03088839.2024.2306943

Lang, S., Bravo-Marquez, F., Beckham, C., Hall, M., & Frank, E. (2019). WekaDeeplearning4j: A deep learning package for WEKA based on Deeplearning4j. Knowledge-Based Systems 178, 48-50. https://doi.org/10.1016/j.knosys.2019.04.013

Lee, K.-H. (2023). An empirical analysis on the price determinants of secondhand ship: Focused on bulk carriers and oil tankers. Korea Maritime & Ocean University.

Mondal, M. A., & Rehena, Z. (2020). Road traffic outlier detection technique based on linear regression. Procedia Computer Science 171, 2547-2555. https://doi.org/10.1016/j.procs.2020.04.276

Morariu, D. I., Creţulescu, R. G., & Breazu, M. (2017). The WEKA multilayer perceptron clasSIFIER. International Journal of Advanced Statistics and IT&C for Economics and Life Sciences, 7, 1. https://magazines.ulbsibiu.ro/ijasitels/index.php/IJASITELS/article/view/17

Pangalos, G. (2023). Financing for a sustainable dry bulk shipping industry: What are the potential routes for financial innovation in sustainability and alternative energy in the dry bulk shipping industry? JRFM, 16, 101. https://doi.org/10.3390/jrfm16020101

Peng, L., Lu, Z., Lei, T., & Jiang, P. (2024). Dual-structure elements morphological filtering and local Z-Score normalization for infrared small target detection against heavy clouds. Remote Sensing, 16, 2343. https://doi.org/10.3390/rs16132343

Perurivenkata, A., Anuradha, Ch., Patnala S. R, C.M., Surya, K.C. (2019). Detecting outliers in high dimensional data sets using Z-Score methodology. IJITEE, 9, 48-53. https://doi.org/10.35940/ijitee.A3910.119119

Pruyn, J. F. J., Van De Voorde, E., & Meersman, H. (2011). Second hand vessel value estimation in maritime economics: A review of the past 20 years and the proposal of an elementary method. Marit Econ Logist, 13, 213-236. https://doi.org/10.1057/mel.2011.6

Rungrattanaubol, J., Na-udom, A., & Harfield, A. (2011). An exploratory neural network model for predicting disability severity from road traffic accidents in Thailand. Proceedings of the Third International Conference on Knowledge and Smart Technologies

Singh, U. S. (2019). Cost estimation using econometric model for restaurant business. QME 20, 217-229. https://doi.org/10.22630/MIBE.2019.20.3.21

Syriopoulos, T., Tsatsaronis, M., & Karamanos, I. (2021). Support vector machine algorithms: An application to ship price forecasting. Comput Econ, 57, 55-87. https://doi.org/10.1007/s10614-020-10032-2

Tsatsaronis, M., Haralambides, H., Syriopoulos, T., & Roumpis, E. (2026). Understanding the dynamics of vessel pricing and investor behavior in dry bulk shipping. Research in Transportation Economics, 115, 101699. https://doi.org/10.1016/j.retrec.2025.101699

Tsolakis, S. D., Cridland, C., & Haralambides, H. E. (2003). Econometric modelling of second-hand ship prices. Marit Econ Logist 5, 347-377. https://doi.org/10.1057/palgrave.mel.9100086

Wang, B., Schultz, G. G., Macfarlane, G. S., Eggett, D. L., & Davis, M. C. (2023). A methodology to detect traffic data anomalies in automated traffic signal performance measures. Future Transportation, 3, 1175-1194. https://doi.org/10.3390/futuretransp3040064

Yaro, A. S., Maly, F., & Prazak, P. (2023). Outlier detection in time-series receive signal strength observation using Z-Score Method with Sn scale estimator for indoor localization. Applied Sciences, 13, 3900. https://doi.org/10.3390/app13063900

Downloads

Published

2026-09-30

How to Cite

Kacprzak, P. (2026). APPLYING MULTILAYER PERCEPTRON AND DATA FILTERING FOR PRELIMINARY SECOND-HAND SHIP PRICE ESTIMATION. Scientific Journal of Gdynia Maritime University, (139), 51–63. https://doi.org/10.26408/139.04

Issue

Section

Articles

Categories