Logo PTI Logo FedCSIS

Position and Communication Papers of the 16th Conference on Computer Science and Intelligence Systems

Annals of Computer Science and Information Systems, Volume 26

Impact of time series clustering on fuel sales prediction results

, ,

DOI: http://dx.doi.org/10.15439/2021F129

Citation: Position and Communication Papers of the 16th Conference on Computer Science and Intelligence Systems, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 26, pages 1321 ()

Full text

Abstract. We investigated the impact of data clustering in the process of predicting demand. We checked different ways of adding information about similar datasets to the forecasting process and we grouped measurements in multiple ways. The experiments were executed on 50 time series describing fuels sales. We used the XGBoost algorithm and some typical time series forecasting methods. We showed a case study for two datasets and we discussed the practical usage of the tested solutions. The results showed that the solution which used XGBoost model utilising data gathered from all available petrol stations, in general, worked the best.

References

  1. E. S. Gardner Jr., “Exponential smoothing: The state of the art,” vol. 4, no. October 1983, pp. 1–28, 1985.
  2. C. W. Chu and G. P. Zhang, “A comparative study of linear and nonlinear models for aggregate retail sales forecasting,” International Journal of Production Economics, vol. 86, no. 3, pp. 217–231, dec 2003. http://dx.doi.org/10.1016/S0925-5273(03)00068-9
  3. A. Krishna, V. Akhilesh, A. Aich, and C. Hegde, “Sales-forecasting of retail stores using machine learning techniques,” in Sales-forecasting of Retail Stores using Machine Learning Techniques. IEEE, 2018. http://dx.doi.org/10.1109/CSITSS.2018.8768765. ISBN 9781538660782 pp. 160–166.
  4. T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. KDD ’16. ACM, 2016. http://dx.doi.org/10.1145/2939672.2939785. ISBN 9781450342322 pp. 785–794. [Online]. Available: http://doi.acm.org/10.1145/2939672.2939785
  5. X. Dairu and Z. Shilong, “Machine Learning Model for Sales Forecasting by Using XGBoost,” in 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE). Institute of Electrical and Electronics Engineers Inc., jan 2021. http://dx.doi.org/10.1109/IC-CECE51280.2021.9342304. ISBN 9781728183190 pp. 480–483.
  6. E. Žunić, K. Korjenić, K. Hodžić, and D. onko, “Application of Facebook’s Prophet Algorithm for Successful Sales Forecasting Based on Real-world Data,” International Journal of Computer Science and Information Technology, vol. 12, no. 2, pp. 23–36, apr 2020. http://dx.doi.org/10.5121/ijcsit.2020.12203
  7. K.-F. Au, T.-M. Choi, and Y. Yu, “Fashion retail forecasting by evolutionary neural networks,” International Journal of Production Economics, vol. 114, no. 2, pp. 615 – 630, 2008. http://dx.doi.org/10.1016/j.ijpe.2007.06.013
  8. V. Adithya Ganesan, S. Divi, N. B. Moudhgalya, U. Sriharsha, and V. Vijayaraghavan, “Forecasting food sales in a multiplex using dynamic artificial neural networks,” in Advances in Intelligent Systems and Computing, vol. 944. Springer Verlag, 2020. http://dx.doi.org/10.1007/978-3-030-17798-0_8. ISBN 9783030177973. ISSN 21945365 pp. 69–80.
  9. C. Giri, S. Thomassey, J. Balkow, and X. Zeng, “Forecasting New Apparel Sales Using Deep Learning and Nonlinear Neural Network Regression,” in 2019 International Conference on Engineering, Science, and Industrial Applications (ICESI). Institute of Electrical and Electronics Engineers Inc., aug 2019. http://dx.doi.org/10.1109/ICESI.2019.8863024. ISBN 9781728121741 pp. 1–6.
  10. Q. Yu, K. Wang, J. O. Strandhagen, and Y. Wang, “Application of Long Short-Term Memory Neural Network to Sales Forecasting in RetailA Case Study,” in Advanced Manufacturing and Automation VII. Springer Singapore, 2018. http://dx.doi.org/10.1007/978-981-10-5768-7_2. ISBN 978-981-10-5768-7. ISSN 18761119 pp. 11–17.
  11. D. Ruta, L. Cen, and Q. H. Vu, “Deep Bi-Directional LSTM Networks for Device Workload Forecasting,” in Proceedings of the 2020 Federated Conference on Computer Science and Information Systems, FedCSIS 2020, 2020. http://dx.doi.org/10.15439/2020F213. ISBN 9788395541674 pp. 115–118.
  12. S. Punia, K. Nikolopoulos, S. P. Singh, J. K. Madaan, and K. Litsiou, “Deep learning with long short-term memory networks and random forests for demand forecasting in multi-channel retail,” International Journal of Production Research, vol. 58, no. 16, pp. 4964–4979, aug 2020. http://dx.doi.org/10.1080/00207543.2020.1735666
  13. J. Chai, S. Wang, and S. Wang, “Demand Forecast of Petroleum Product Consumption in the Chinese Transportation Industry,” Energies, vol. 5, no. 3, pp. 577–598, 2012. http://dx.doi.org/10.3390/en5030577. [Online]. Available: www.mdpi.com/journal/energiesArticle
  14. I. Themido, A. Quintino, and J. Leitao, “Modelling the Retail Sales of Gasoline in a Portuguese Metropolitan Area,” International Transactions in Operational Research, vol. 5, no. 2, pp. 89–102, mar 1998. http://dx.doi.org/10.1111/j.1475-3995.1998.tb00106.x. [Online]. Available: http://doi.wiley.com/10.1111/j.1475-3995.1998.tb00106.x
  15. K. Kalid, J. Ahmad, S. Yong, and K. H. Yew, “Petronas Petrol Station Fuel Consumption Forecast System,” in Proceedings of the Second International Conference on Artificial Intelligence in Engineering & Technology, 2004. http://dx.doi.org/10.13140/2.1.4493.8568. ISBN 10.13140/2.1.4. [Online]. Available: https://www.researchgate.net/publication/271637545
  16. S. M. Rizvi, T. Syed, and J. Qureshi, “Real-time forecasting of petrol retail using dilated causal CNNs,” Journal of Ambient Intelligence and Humanized Computing, vol. 1, p. 3, feb 2021. http://dx.doi.org/10.1007/s12652-021-02941-3. [Online]. Available: https://doi.org/10.1007/s12652-021-02941-3
  17. P. F. Jiménez-Pérez and L. Mora-López, “Modeling and forecasting hourly global solar radiation using clustering and classification techniques,” Solar Energy, vol. 135, pp. 682–691, oct 2016. http://dx.doi.org/10.1016/j.solener.2016.06.039
  18. B. Nepal, M. Yamaha, A. Yokoe, and T. Yamaji, “Electricity load forecasting using clustering and ARIMA model for energy management in buildings,” Japan Architectural Review, vol. 3, no. 1, pp. 62–76, jan 2020. http://dx.doi.org/10.1002/2475-8876.12135. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/2475-8876.12135
  19. S. Thomassey and A. Fiordaliso, “A hybrid sales forecasting system based on clustering and decision trees,” Decision Support Systems, vol. 42, no. 1, pp. 408–421, oct 2006. http://dx.doi.org/10.1016/j.dss.2005.01.008
  20. S. Aghabozorgi, A. Seyed Shirkhorshidi, and T. Ying Wah, “Time-series clustering - A decade review,” Information Systems, vol. 53, pp. 16–38, may 2015. http://dx.doi.org/10.1016/j.is.2015.04.007
  21. Ł. Sosnowski, I. Szymusik, and T. Penza, “Network of Fuzzy Comparators for Ovulation Window Prediction,” in Information Processing and Management of Uncertainty in Knowledge-Based Systems, M.-J. Lesot, S. Vieira, M. Z. Reformat, J. P. Carvalho, A. Wilbik, B. Bouchon-Meunier, and R. R. Yager, Eds. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-50153-2_59. ISBN 978-3-030-50153-2 pp. 800–813.
  22. M. Blachnik and J. Henzel, “Estimating the Performance Indicators of Promotion Efficiency in FMCG Retail,” in Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science, vol. 12533. Springer, Cham, 2020. http://dx.doi.org/10.1007/978-3-030-63833-7_27. ISBN 9783030638320. ISSN 16113349 pp. 320–332.
  23. J. Henzel and M. Sikora, “Gradient Boosting and Deep Learning Models Approach to Forecasting Promotions Efficiency in FMCG Retail,” in Artificial Intelligence and Soft Computing. ICAISC 2020. Lecture Notes in Computer Science, vol. 12416. Springer, Cham, 2020. http://dx.doi.org/10.1007/978-3-030-61534-5_30. ISBN 978-3-030-61533-8. ISSN 16113349 pp. 336–345.