Financial markets are characterized by high levels of randomness and complexity, which makes it very difficult to predict stock prices. In the stock market, the anticipations concerning the possible fluctuations in stock’s prices hold significant importance in the financial field, as these expectations have a direct impact on the decisions that are taken in the spheres of investment, risk minimization and market effectiveness. Accurate forecasting enables institutional investors, hedge funds and retail traders to implement data-driven strategies in relation to portfolio allocation and risks return levels. In this work, therefore, we suggest an improved approach to stock price prediction based on deep learning techniques. We select the NIFTY Midcap 50 index values of National Stock Exchange (NSE) of India, over a period of 11 years: 2013–2023. The historical data for the high value of NIFTY MIDCAP 50 for the years 2013–2023. By using a deep learning technique known as the Long Short-Term Memory (LSTM) model, we predict the high value of NIFTY MIDCAP 50 for year 2024 with forecast horizon of one day. This model aims to produce low error in the predictions of the high prices of the NIFTY Midcap 50 index.