• Jyothirmai Samboji
• P.R. Prathyusha
• Mohammed Turab
• Singareddy Keerthana Reddy

Predicting stock values is challenging but very important as far as investors are concerned. The classical way of forecasting is way too vague as the markets are related with each other. To deal with this issue, the use of sophisticated algorithms such as the Artificial Neural Network (ANN) and the Long Short Term Memory (LSTM) model are employed. These methods add weights for each data point employing procedures like stochastic gradient descent which ensures the exact forecasts. Nonetheless, there’s a gap between supporters of efficient market hypothesis and those who suppose a perfectly precise forecast model will have an impact. Model performance is determined by quite a lot of different issues such as input data, algorithms, and selection criteria. Timing deconstruction is also significant for precise forecasts. New domains, mainly machine learning and deep learning, have shown their effectiveness in stock analysis. Because of progress, nevertheless, the forecasting technique is hardly ever accurate. The market reticence and the complexity hamper the forecasting method. LSTM and ANN are well-versed in capturing the intricate density of time-series data and thus, they assist in more reliable forecasts.

Stock values, Forecasting, Artificial Neural Network (ANN), Long Short Term Memory (LSTM) model, Stochastic gradient descent, Efficient market hypothesis, Model performance, Input data, Timing deconstruction, Machine learning, Deep learning, Stock movement analysis, Market reticence, Complexity, Forecast accuracy, Time-series data, Reliable forecasts

"Deep Learning Techniques based Stock Price Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.d595-d598, April-2024, Available :http://www.jetir.org/papers/JETIR2404375.pdf

"Deep Learning Techniques based Stock Price Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppd595-d598, April-2024, Available at : http://www.jetir.org/papers/JETIR2404375.pdf