• KAMBAMPATI BALA KRISHNA
• SUNKU SAI ABHINAV
• SUNKARA HEMA DURGA PRASAD
• S.NALINI POORNIMA

Stock price forecasting is a dynamic and intricate task based on the nature of financial market volatility. Conventional statistical models fail to capture long-term dependencies and nonlinear stock price movement patterns. This paper introduces the use of Long Short Term Memory (LSTM) networks, a type of specialized recurrent neural networks (RNNs), for precise stock price forecasting. LSTM model is trained to learn and remember sequence patterns in stock financial data in an efficient way, avoiding the vanishing gradient problem that confines typical RNNs. Stocks' historical prices such as open, high, low, close prices, and volume are used as salient input features for model training and testing. Experimental findings indicate that LSTM performs better than traditional methods by successfully extracting temporal dependencies, resulting in improved forecasting accuracy. This research highlights the capabilities of deep learning for financial market analysis, giving a glimpse of its practical use for investors and analysts. The results indicate that LSTM-based models can be used as efficient tools for predictive stock market analysis, enabling well-informed decision-making and risk management planning.

"STOCK PRICE PREDICTION USING LONG SHORT TERM MEMORY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 4, page no.k672-k678, April-2025, Available :http://www.jetir.org/papers/JETIR2504A84.pdf

"STOCK PRICE PREDICTION USING LONG SHORT TERM MEMORY", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 4, page no. ppk672-k678, April-2025, Available at : http://www.jetir.org/papers/JETIR2504A84.pdf