Articles

Stock Price Forecasting on Time Series Data Using the Long Short-Term Memory (LSTM) Model

/0 Comments/in /by

Stock price forecasting on time series data is a complex task due to the dynamic and uncertain nature of financial markets. This research aims to forecast stock prices by applying an advanced machine learning model, namely Long Short-Term Memory (LSTM), a deep learning architecture that excels in capturing long-term dependencies in time series data. The dataset used in this study consists of 1221 daily ANTM.JK stock price data over the period April 30, 2019 to April 30, 2024. The model was trained and evaluated using performance metrics such as Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) in measuring the level of forecasting accuracy. The results show that the LSTM model can accurately predict stock prices on time series data, as evidenced by the MAPE accuracy evaluation value of 2.52% and RMSE of 54.64. These findings indicate that the LSTM model is effective in predicting stock prices on time series data and can be used as a supporting tool in making the right investment decisions.

Prediction of Stock Price Volatility Using the Long Short Term Memory (LSTM) Model for Investment Portfolio Selection Strategy

/in /by

Volatility is an important variable in financial data models. Predicting volatility in financial data is helpful for investors to make good decisions to reduce risk and to gain investment returns. In predicting volatility, many researchers have conducted research in building prediction models using data mining. This research uses a deep learning algorithm, namely Long Short Term Memory (LSTM) which has high accuracy compared to other models. The research aims to predict stock price volatility and for investment portfolio selection. The object of this study is the historical stock price of PT. Unilever Indonesia Tbk. (UNVR), PT. Fast Food Indonesia Tbk. (FAST) which manages KFC and PT. MAP Boga Adiperkasa Tbk. (MAPB) which manages Starbucks in the period 2023 to 2024, when there was a boycott caused by the war between countries that occurred in the Middle East. The data is analysed using the LSTM model where stock price volatility was determined by the variance of the return and log return on the next seven days, then using LSTM the stock price volatility data was predicted. The results show that the MSE and RMSE values are very small, which means that the volatility prediction results are almost the same as the actual data. And the average volatility prediction results in UNVR stock of 0.00841, MAPB stock of 0.01717, and FAST stock of 0.01323. From these results can be used as a reference for the selection of investment portfolios.

A Comparison of Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) in River Water Quality Prediction

/in /by

River water is a crucial natural resource utilized for various purposes, including agriculture and drinking. Human activities such as mining, industrial discharge, and improper waste management contribute to river water pollution, affecting its quality and posing risks to human health. Monitoring and predicting river water quality are essential for effective management and pollution control. The research focuses on Dissolved Oxygen (DO), and comparing of Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) to developed prediction models. Evaluation of the models’ performance shows that the ANN model outperforms LSTM in predicting Dissolved Oxygen (DO) concentrations, achieving lower Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Although LSTM exhibits lower Mean Squared Error (MSE), the ANN model demonstrates better accuracy in minimizing the average distance between predicted and actual values. The findings suggest that ANN-based models offer good performance in river water quality prediction, with potential for further enhancement through additional variables or model architecture adjustments.