Sequential Pattern Mining untuk Data Transaksi Penjualan Supermarket menggunakan Algoritme Generalized Sequential Pattern

  • Albert Kurniawan Universitas Kristen Satya Wacana
  • Ramos Somya Universitas Kristen Satya Wacana


Online supermarket sales transaction data is a sequence dataset. This data stores purchase transaction data made by customers, so it can be analyzed using Market Basket Analysis (MBA) approach. The problem that is often experienced by supermarkets is the difficulty of implementing the accurate sales strategy to consumers. Based on these problems, this research will analyze the West Superstore supermarket dataset based on the MBA approach. The algorithm used is the Generalized Sequential Pattern (GSP) algorithm, where this algorithm can generate frequent items and sequence patterns, so that the resulting rules can be more accurate. The GSP algorithm in this study is implemented in the Python programming language. The test results show that the output of Python is in accordance with the output of the GSP algorithm calculation. The time required for rule generation in the GSP algorithm also depends on the number of records being used. The more number of sales transactions to be analyzed, it needs longer time in computation. The analysis conducted on the sales dataset at the West Superstore resulted in 391 rules, where these rules can be used by supermarkets to implement their sales strategies.


[1] M. Kaur and S. Kang, “Market Basket Analysis: Identify the Changing Trends of Market Data Using Association Rule Mining,” Procedia Comput. Sci., vol. 85, no. Cms, pp. 78–85, 2016, doi: 10.1016/j.procs.2016.05.180.
[2] F. Kurniawan, B. Umayah, J. Hammad, S. M. S. Nugroho, and M. Hariadi, “Market Basket Analysis to Identify Customer Behaviours by Way of Transaction Data,” Knowl. Eng. Data Sci., vol. 1, no. 1, p. 20, 2017, doi: 10.17977/um018v1i12018p20-25.
[3] Rizkybayunovrianto and Muslim, “Penerapan Metode Market Basket Analysis pada Minimarket Toko Baru,” Indones. J. Data Sci., vol. 1, no. 1, pp. 1–5, 2020, doi: 10.33096/ijodas.v1i1.2.
[4] D. Gunawan, “Pengembangan Aplikasi Market Basket Analysis Menggunakan Algoritma Generalized Sequential Pattern pada Supermarket,” Semin. Nas. Apl. Teknol. Inf., pp. 1–6, 2015.
[5] A. Santoso, T. Pradana, and Ulyontang, “Penggalian Kaidah Multilevel Association Rule Dari Data Mart Swalayan Asgap Krian,” Ideatech, pp. 67–75, 2015.
[6] P. N. Sabrina, “Penerapan Sequential Pattern Mining pada Data Pemesanan untuk Strategi Penawaran dan Pemasaran Produk,” Annu. Res. Semin. 2016, vol. 2, no. 1, pp. 449–455, 2016.
[7] F. Marisa, “Educational Data Mining (Konsep dan Penerapan),” Teknol. Inf., vol. 4, no. 2, pp. 90–97, 2014.
[8] R. Srikant and R. Agrawal, “Mining sequential patterns: Generalizations and performance improvements,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 1057 LNCS, pp. 3–17, 1996, doi: 10.1007/bfb0014140.
[9] R. A. R. Srikant, “Mining Sequential Patterns,” in Proceedings of the Eleventh International Conference on Data Engineering, 1995, doi: 10.1109/ICDE.1995.380415.
[10] I. S. Sitanggang, N. A. Husin, A. Agustina, and N. Mahmoodian, “Sequential pattern mining on library transaction data,” Proc. 2010 Int. Symp. Inf. Technol. - Vis. Informatics, ITSim’10, vol. 1, pp. 7–10, 2010, doi: 10.1109/ITSIM.2010.5561316.
[11] C. H. Mooney and J. F. Roddick, “Sequential pattern mining - Approaches and algorithms,” ACM Comput. Surv., vol. 45, no. 2, 2013, doi: 10.1145/2431211.2431218.