Prediksi Penjualan Supermarket Menggunakan Pendekatan Deep Learning
DOI:
https://doi.org/10.31154/cogito.v7i1.306.160-169Abstract
Berdasarkan data transaksi tahun 2014 sampai 2016 dari salah satu supermarket yang ada di Taiwan, penulis menghasilkan analisa model prediksi dengan menguji data menggunakan metode Deep Learning. Beberapa faktor yang berpengaruh telah di dipelajari dan berguna untuk input prediksi, antara lain keadaan cuacu, diskon, hari raya, dan lain sebagainya. Motivasi utama dari penelitian yang penulis lakukan adalah menggunakan teknologi yang berhubungan dengan eksplorasi data untuk memprediksikan penjualan dari produk-produk dan waktu berkunjung pelangan dalam industry retail, untuk mencari grup target yang tepat dan korelasi produk yang tinggi. Pada akhirnya penulis menciptakan sistem keputusan produk yang berisi analisa visual dan tindakan saran untuk manajer produk pemasaran serta pemangku kepentingan dalam pemasaran produk. Dengan adanya hasil prediksi ini, diharapkan dapat menbantu manajer atau pemangku kepentingan lainnya untuk dapat memasarkan serta menjual produk secara tepat sehingga dapat menghasilkan keuntungan yang banyak dengan menggunkan analisa prediksi yang kami buat. LSTM merupakan model yang sering dipakai dalam Recursive Neural Network (RNN), dan pada dasarnya berfungsi untuk memecahkan masalah dari Time Series. Model Deep Learning yang penulis gunakan adalah Long Short Term Memory (LSTM), dimana model ini menyediakan analisa dan prediksi dari serangkaian data. Sebagai contoh, pada saat akhir pekan pengunjungnya melonjat, maka time machine learning ini akan menambahkan pengartian dari nilai parameter akhir pekan dan nilai ouputnya memiliki korelasi yang kuat.Kata kunci—Predictions, Time Series, LSTM, RNN, Deep LearningReferences
Tombeng, M. T., Kandow, H., Adam, S. I., Silitonga, A., Korompis, A., 2019, Android-Based Application To Detect Drowsiness When Driving Vehicle, IEEE 1st International Conference on Cybernetics and Intelligent System (ICORIS), pp. 100-104
Liang, J. F., 2013, Applying Data Mining Techniques on Retailing Industry – A Case Study on Speciality Chain Store, Master Thesis, National Taipei University Department of Business Administration.
Chang, Y. C., 2015, A Study on Database Marketing Strategy of 3C Chain Stores, Master Thesis, National Kaoshiung First University of Science and Technology Department of Marketing and Distribution Management.
Shih, M. H., 2013, Applying Data Mining to Customer Relationship Management – A study on Construction Materials Retail Business, Master Thesis, Tunghai University Department of Industrial Engineering.
Dong, D., Shen, Z., Yang, T., 2018, Wind Power Prediction based on Recurrent Neural Network with Long Shor-term Memory Units, 2018 IEEE Internation Conference on Renewable Enery and Power Engineering, pp. 34-38.
Lu, H., Yang, F., 2018, Research on Network Traffic Prediction Based on Long Short-Term Memory Neural Network, 2018 IEEE 4th International Conference on Computer and Communications, pp. 1109-1113.
Yangzhen, F., Hong, Z., Chenchen, Z., Chao, F., 2017, A Software Reliability Prediction Model, 2017 IEEE International Conference on Software Quality, Reliability, and Security (Comanion Volume), pp. 614-615.
Sandag, G., 2020, Prediksi Rating Aplikasi App Store Menggunakan Algoritma Random Forest, CogITo Smart Journal Fakultas Ilmu Komputer Universitas Klabat, vol 6, no 2, pp. 167-178.
McQueen, J. B., 1967, Some Methods of Classification and Analysis of Multivariate Obsevations, Proceedings of the 5th Berkeley Symposium on Mathematical Statistic and Probability, pp. 281-297.
LSTM Model, https://en.wikipedia.org/wiki/Long_short-term_memory, diakses tgl 23 Februari 2020.
Berry, M. J. A, Linoff, G. S., 2011, Data Mining Techniques: for Marketing, Sales, and Customer Relationship Management, Vol. 1, Ed. 1, Wiley Computer Publishing, Hoboken NJ.
Charlet, L., Annie, M. C., Kumar, D. A., 2012, Market Basket Analysis for a Supermarket Based on Frequent Item Set Mining, International Journal of Computer Science Issues, 9(3), pp. 257.
Schmitt, J., 2010, Drawing Association Rules between Purchases and In-Store Behavior: An Extension of the Market Basket Analysis, Advances in Consumer Research, 37, pp. 899-901.
Adomavicius, G., Tuzhilin, A., 2005, Incorporating Contextual Information in Recommender System Using a Multidimensional Approach, ACM Transactions on Information System, Vol. 23(1), pp. 103-145.
Kohavi, R., Parekh, R., 2004, Visualizing RFM Segmentation, Proceedings of the 2004 SIAM International Conference on Data Mining (SDM’2004), Orlando, FL, pp. 391-399.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
