ANALYSIS OF ACCURACY LEVEL OF MOVING AVERAGE, PARABOLIC SAR AND CONVOLUTIONAL INDICATORS NEURAL NETWORK  ON BUY AND SELL DECISIONS  (Case study of shares of PT Bank Negara Indonesia, Tbk)

Axmal Fauza; Evi Noviaty

Authors

Axmal Fauza Universitas Mohammad Husni Thamrin, Jakarta
Evi Noviaty Universitas Mohammad Husni Thamrin, Jakarta

Keywords:

Stocks, Accuracy Moving, Average Paraboic SAR, Convolutional Neural Network

Abstract

The development of the global COVID-19 pandemic in the fourth quarter of 2021 was marked by the increase in global daily cases after the reopening in various countries and the emergence of Omicron as a new variant of concern. The banking sector is one of the main sectors supporting the Indonesian economy. As we enter the era of the industrial revolution 4.0, people see the capital market as a reliable source of income to increase their income. This is evidenced by the large number of foreign and local investors who invest their capital in the world capital market. The movement of stock prices on the Indonesian stock exchange is very volatile. This is a risk that must be borne by every investor, especially short-term investors. Many methods are used in predicting the stock price, one of which is by using technical analysis indicators such as the Moving Average and Parabolic SAR. In addition to using technical analysis in making investment decisions, investors can also use machine learning algorithmic indicators such as the Convolutional Neural Network. By using the tradingview website application and the AXMAL 1.0 mobile application in collecting data and also analyzing data on stock price movements of PT. Bank Negara Indonesia Tbk., it is obtained that the results of the Convolutional Neural Network indicator accuracy are greater than the Moving Average and Parabolic SAR indicators, which are 56.1% and also produce a higher return of 27.14% during the 2021 period, while the Parabolic SAR indicator produces an accuracy level which is the same as the Moving Average indicator, which is 33.3% but produces a positive return of 12.51% while the Moving Average indicator produces a negative return of-4.46%.

Downloads

Download data is not yet available.

References

I. Marzuki et al., COVID-19: seribu satu wajah. Yayasan Kita Menulis, 2021.

E. Widanengsih, Y. Yusuf, and R. Faisal, “PENGARUH ASIMETRI INFORMASI DAN MANAJEMEN LABA TERHADAP COST OF EQUITY CAPITAL PADA EMITEN PERBANKAN,” J. Akunt. Dan Bisnis Indones., vol. 3, no. 2, pp. 117–124, 2022.

H. B. Simatupang, “Peranan perbankan dalam meningkatkan perekonomian indonesia,” JRAM (Jurnal Ris. Akunt. Multiparadigma), vol. 6, no. 2, pp. 136–146, 2019.

S. Safuridar and Z. Asyuratama, “Analisis Indikator Makro Ekonomi terhadap Harga Saham Sektor Perbankan,” J. Samudra Ekon., vol. 2, no. 2, pp. 138–146, 2018.

A. Savitri, Bonus Demografi 2030: menjawab tantangan serta peluang edukasi 4.0 dan revolusi bisnis 4.0. Penerbit Genesis, 2019.

W. Y. Agusti, “Pengaruh profitabilitas, leverage, dan corporate governance terhadap tax avoidance (studi empiris pada perusahaan manufaktur yang terdaftar di BEI tahun 2009-2012),” J. Akunt., vol. 2, no. 3, 2014.

Y. Yusuf and L. Anthoni, “PERBANDINGAN PERGERAKAN INDEKS HARGA SAHAM GABUNGAN (IHSG) DENGAN INDEKS SAHAM SYARIAH INDONESIA (ISSI) SELAMA PANDEMI COVID 19,” in PROSEDING SEMINAR NASIONAL AKUNTANSI, 2020, vol. 3, no. 1.

R. C. Gumilang, R. R. Hidayat, and M. Np, “Pengaruh variabel makro ekonomi, harga emas dan harga minyak dunia terhadap indeks harga saham gabungan (Studi pada bursa efek indonesia periode 2009–2013),” J. Adm. Bisnis, vol. 14, no. 2, 2014.

D. D. P. Asthri, T. Topowijono, and S. Sulasmiyati, “Analisis Teknikal Dengan Indikator Moving Average Convergence Divergence untuk Menentukan Sinyal Membeli dan Menjual Dalam Perdagangan Saham (Studi Pada Perusahaan Sub Sekto Makanan Dan Minuman Di Bei Tahun 2013-2015).” Brawijaya University, 2016.

E. Ong, Technical Analysis For Mega Profit (Hc). Gramedia Pustaka Utama, 2016.

D. Wira, “Mengenal Investasi Saham,” Jakarta JurusCuan. com, 2019.

F. Frankandinata and Y. Cahyadi, “Analisis Keakuratan Indikator Bollinger Bands Terhadap Pergerakan Harga Saham: Studi Kasus pada Saham PT Astra Agro Lestari Tbk,” Binus Bus. Rev., vol. 5, no. 1, pp. 112–122, 2014.

J.-H. Park et al., “Automated identification of cephalometric landmarks: Part 1—Comparisons between the latest deep-learning methods YOLOV3 and SSD,” Angle Orthod., vol. 89, no. 6, pp. 903–909, 2019.

N. H. Tran et al., “Deep learning enables de novo peptide sequencing from data-independent-acquisition mass spectrometry,” Nat. Methods, vol. 16, no. 1, pp. 63–66, 2019.

W. Sugiarto, Y. Kristian, and E. R. Setyaningsih, “Estimasi Arah Tatapan Mata Menggunakan Ensemble Convolutional Neural Network,” Teknika, vol. 7, no. 2, pp. 94–101, 2018.

I. Putra, “Klasifikasi citra menggunakan convolutional neural network (CNN) pada caltech 101.” Institut Teknologi Sepuluh Nopember, 2016.