Paper Title
Applying CNN-LSTM Based Model For Stock Price Prediction: A Deep Learning Approach

Abstract
Investment involves the allocation of financial resources with the objective of generating future profits. Prior to making investment decisions in the stock market, investors are required to undertake a range of analyses to enhance profit potential and mitigate risks. Two commonly used analysis methods are fundamental analysis, which studies the financial condition and performance of companies, and technical analysis, which focuses on patterns and trends in stock prices. Currently, deep learning technologies, a subset of artificial intelligence, are employed to assist in predicting stock price fluctuations, utilizing models such as GRU, MLP, RNN, CNN, and LSTM.". The study focuses on using a hybrid deep learning model, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for stock price prediction. The research methodology involves testing the CNN-LSTM model on data from 10 companies consistently listed in the LQ 45 Index, a prominent Indonesian stock market index. The dataset encompasses ten years of daily transactions, focusing on the model's ability to accurately predict closing stock prices.. Performance metrics like Mean Squared Error (MSE), Mean Absolute Error (MAE), and R2 Score are used for evaluation. The results indicate that the CNN-LSTM model effectively predicts stock prices, evidenced by low MSE and MAE values, along with high R² scores across various datasets. The study concludes that the CNN-LSTM model is effective for stock market analysis and can aid investors in making data-driven decisions. However, it emphasizes the need for combining such models with comprehensive financial analysis for better investment. Keywords - CNN, LSTM, Stock Market, Stock Price Prediction