Due to the potential for profits and the opportunity to invest instantaneously in specific businesses, stocks remain people’s most common investment option. Forecasting the stock market flow is crucial for market individuals because even a tiny increase in estimation preciseness could result in making better trading choices than their competitors. Various studies focused on forecasting stock market movement using different learning methods and parameters. These market data are commonly forecasted using statistical methods, machine learning, deep-learning models, and combinations. This research seeks to take advantage of the Long Short-Term Memory(LSTM) layers’ efficiency in detecting both short-term and long-term relationships and the convolutional layers’ capacity for grasping the internal structure of stock market data. The study used the Agricultural Development Bank Limited (ADBL) stock price data from the Nepal stock market for demonstration. In experimentation, we compared the suggested model to state-of-the-art deep learning techniques. The results illustrate that the Convolutional Neural Network-LSTM (CNN-LSTM) model performs significantly better than typical deep-learning models.