• Halesh T G K
• Harish Kumar
• Harsha E
• Dr. Anitha S Sastry

Although stock price is dynamic and complex in nature, forecasting their movement has been shown to be a challenging task. Conventional models frequently fail to identify the complex connections and patterns found in stock market data. Deep learning methods, especially Long Short-Term Memory (LSTM) networks, have demonstrated encouraging in a number of time series predication problems in recent years. The use of LSTM networks for stock price predication is examined in this work. In order to reduce overfitting, we suggest a novel LSTM-based model that combines several layers of LSTM cells with dropout regularization. To further improve the model’s anticipating power, we use previous price data and technical indication as input characteristic. We test our approach using real-world market datasets and evaluate its effectiveness against conventional time series forecasting model. In this paper, a new LSTM built with the Dash web application development framework in python is presented. The experiment results demonstrate that our LSTM-based methodology outperforms baseline approaches and delivers better stock price accuracy in forecasting. Additionally, we examine the effects of various input features and hyper parameters on the prediction performance, offering valuable perspectives on the development and enhancement of long short-term memory (LSTM) model intended for stock price predication. The user-friendly platform for investigating and evaluating stock price forecast is made possible by combination of LSTM with Dash, which offers insightful information to financial market researchers and investors alike. In brief, our research advanced the using of deep learning method in financial forecasting and provides practitioners and scholars in the field of quantitative finance with insightful information.

Stock price predication, LSTM, Dash, Deep learning, Dropout regularization, Web applications.

"Smart Investment: Advancing Stock Market Predictions Through ML And DL Using LSTM.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.p89-p95, May-2024, Available :http://www.jetir.org/papers/JETIR2405G15.pdf

"Smart Investment: Advancing Stock Market Predictions Through ML And DL Using LSTM.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppp89-p95, May-2024, Available at : http://www.jetir.org/papers/JETIR2405G15.pdf