• NANNAM SWETHA

Financial market predictions are challenging in the best of times and especially when markets experience economic distress or rapid flux. This study aims to find better prediction models using AI and significant learning computations. It looks at four trade areas for testing appraisals: widened financials, oil, non-metallic minerals, and key metals from the Tehran stock exchange. This study investigates nine AI models (Decision Tree, Random Forest, adaptive boosting (Adaboost), eXtreme gradient boosting (XGBoost), support vector classifiers (SVC), Naïve Bayes, K-nearest neighbors (KNN), logistic regression, and artificial neural network (ANN) along with two significant learning procedures, recurrent neural network (RNN) and long short-term memory (LSTM). We look at ten specific markers from ten years of data and two distinct ways of assessing them. Each assumption model is surveyed by three estimations subject to the data. Our results show that for the perpetual data, RNN and LSTM are superior to other prediction models with noteworthy differentiation. Results further show that in the combined data evaluation, those significant learning techniques work exceedingly well

Stock market, trends prediction, classification, machine learning, deep learning.

"PREDICTING STOCK MARKET TRENDS USING MACHINE LEARNING AND DEEP LEARNING ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 10, page no.a182-a188, October-2021, Available :http://www.jetir.org/papers/JETIR2110025.pdf

"PREDICTING STOCK MARKET TRENDS USING MACHINE LEARNING AND DEEP LEARNING ALGORITHM", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 10, page no. ppa182-a188, October-2021, Available at : http://www.jetir.org/papers/JETIR2110025.pdf