Analyzing LQ45 Prices Using Indonesia's Inflation Rate with a Hybrid ARIMA-LSTM Model

This study investigates the relationship between Indonesia's inflation rate and fluctuations in LQ45 stock prices from 2003 to 2024, with a focus on predicting stock prices using a hybrid ARIMA-LSTM model. By integrating ARIMA's strength in modeling long-term trends and LSTM's ability to capture short-term fluctuations, the hybrid model provides more accurate stock price predictions. The results show a negative correlation between inflation and LQ45 stock prices, with the ARIMA-LSTM model outperforming individual models in terms of prediction accuracy. The research applies Spearman's Rank Correlation to measure the correlation between inflation rates and LQ45 stock prices, aiming to determine the impact of inflation on stock price changes. Additionally, the study employs a hybrid prediction model combining ARIMA (Autoregressive Integrated Moving Average) and LSTM (Long Short-Term Memory) to enhance the accuracy of stock price forecasts. ARIMA is leveraged to capture long-term linear trends, while LSTM identifies short-term nonlinear patterns By integrating these two methods, the hybrid ARIMA-LSTM model capitalizes on ARIMA’s ability to analyze long-term data and LSTM’s strength in managing short-term fluctuations. The findings reveal that the hybrid model produces more accurate stock price predictions, especially in volatile market conditions influenced by inflation changes.