Prediksi Harga Saham Menggunakan Generalize Fuzzy Inference System (GENFIS3)
The stock market has been very hard hit during the Covid 19 pandemic, many stock prices have plummeted which is influenced by negative sentiment in the form of uncertainty about when this Covid will end. On the other hand, this situation is a very big opportunity to invest because it buys cheap stock prices. Prediction is an instrument that can assist in making decisions about buying and selling shares. We can process daily time series data of stock prices as a reference in estimating the ups and downs of stock prices. In this study, the data used are daily data on the highest stock prices
during the Covid-19 period. This data pattern formation is assumed with six days as input and the seventh day as the expected target. The data pattern that is formed is divided into two parts, namely the training data pattern and the test data pattern. The prediction method used is the Generalize Fuzzy Inference System (Genfis3). Genfis3 is a combination of Fuzzy C-Means and Adaptive Neural Fuzzy Inference (ANFIS). The training data will be clustered into 3 (low, medium and high) using FCM then the membership function of each cluster will be entered into ANFIS to form an inference engine. Based on the results of the research, Genfis 3 could recognize the pattern of training data well with a MAPE of 3.7%. Based on the test with the test data pattern, GENFIS 3 is able to predict the test data pattern very well with a MAPE of 2.24%.
Azizah, N. (2016). Metode Adaptive Neuro Fuzzy Inference System (ANFIS) untuk Prediksi Tingkat Layanan Jalan. Jurnal Sistem Informasi Bisnis, 3(3), 98–103. https://doi.org/10.21456/vol3iss3pp
Finance, Y. (2020). PT Bank Tabungan Negara (Persero) Tbk (BBTN.JK). Historical Data. https://finance.yahoo.com/quote/BBTN.JK/history?p=BBTN.JK
Novita, A. (2016). Prediksi Pergerakan Harga Saham Pada Bank Terbesar Di Indonesia Dengan Metode Backpropagation Neural Network. Jutisi, 05(01), 965–972.
Purnama, R. B. (2017). Perancangan Prediksi Untuk Menentukan Indeks Harga Saham Menggunakan Jaringan Syaraf Tiruan. Kinetik, 2(2), 125. https://doi.org/10.22219/kinetik.v2i2.190
Rochman, E. M. S., & Djunaidy, A. (2014). Prediksi Harga Saham Yang Mempertimbangkan Faktor Eksternal Menggunakan Jaringan Saraf Tiruan. Jurnal Ilmiah NERO, 1(2), 5–11.
Setiawan, W. (2008). PREDIKSI HARGA SAHAM MENGGUNAKAN JARINGAN SYARAF TIRUAN MULTILAYER FEEDFORWARD NETWORK DENGAN ALGORITMA BACKPROPAGATION. Konferensi Nasional Sistem Dan Informatika 2008, November, 108–113. https://doi.org/10.13140/2.1.3467.5525
Sitohang, S., Girsang, A. S., & Suharjito. (2017). Prediction of the number of airport passengers using fuzzy C-means and adaptive neuro fuzzy inference system. International Review of Automatic Control, 10(3), 280–287. https://doi.org/10.15866/ireaco.v10i3.12003
Sitohang, S., & Siringo, A. M. (2018). Analisis Peramalan Harga Emas Dengan Metode Automatic Clustering And Fuzzy Logic Relationship. Jurnal ISD, 3(2).
Sungkawa, I., & Megasari, R. T. (2011). Penerapan Ukuran Ketepatan Nilai Ramalan Data Deret Waktu dalam Seleksi Model Peramalan Volume Penjualan PT Satriamandiri Citramulia. ComTech: Computer, Mathematics and Engineering Applications, 2(2), 636. https://doi.org/10.21512/comtech.v2i2.2813
This work is licensed under a Creative Commons Attribution 4.0 International License.