Peramalan Harga Saham Pertambangan Pada Bursa Efek Indonesia (BEI) Menggunakan Long Short Term Memory (LSTM)

Roby Julian (Universitas Multi Data Palembang)
Muhammad Rizky Pribadi (Universitas Multi Data Palembang)

JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI
Vol 8 No 3 (2021): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)

Stock investment is one of the right choices to get more profit. However, in investing in stocks, it is necessary to analyze the data of a company that can determine the rise or fall of a stock price in the company. Very dynamic movements require data modeling to predict stock prices in order to get a high level of accuracy. An algorithm was developed to solve the problem of long-term data or historical data, namely Long Short Term Memory (LSTM). By using the Long Short Term (LSTM) this study produces a fairly good RMSE value with an increase in the RMSE value based on the addition of the number of epoch variations. The optimal epoch variation was obtained with the number of epochs of 200. Meanwhile, the optimal RMSE value produced by the Long Short Term Memory (LSTM) method was generated by TINS issuers with an RMSE of 31.71.