• Ruhani Ruhal
• Er. Vandana Prashar

The stock market contains numerous challenges to investors, ranging from volatility and excessive workload of information to behavioral factors and market manipulation. Stock market forecasting is crucial in addressing these challenges since it provides investors with valuable insights that aid in decision-making, risk management, and long-term investment planning. Investors can improve their understanding of market dynamics and their chances of achieving positive investment outcomes by leveraging predictive models and advanced analytics. There are various approaches for forecasting stock prices, both conventional statistics-based approaches and machine learning based advance and automated algorithms. Machine learning (ML) based algorithms are categorized as four different approaches, namely, Traditional ML approaches, deep learning & neural networks, time series analysis and graph-based approaches. While no single method can guarantee accuracy, combining multiple techniques or to use ensemble methods to improve forecasting performance is frequently advantageous. During the research of various algorithms for stock market prediction, it was discovered that moving averages work well with small datasets of historical data for descriptive analysis. According to the research works cited in this review paper, traditional statistical methods are incapable of taking into account many extra factors such as semantic factors, making them less accurate than machine learning approaches. Whereas, among machine learning approaches, Deep learning and neural networks have been identified as the best options for developing automated models and, Graph-based methods used in conjunction with these approaches can help the system connect the features.

stock market prediction, comparative study of conventional methods and machine learning methods, machine learning, graph, neural networks, deep learning, semantics, traditional machine learning, moving averages, ARIMA, statistical methods, stock market analysis

"A Comparative Study Of Statistical Methods And Machine Learning Approaches For Stock Price Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.g156-g161, July-2023, Available :http://www.jetir.org/papers/JETIR2307623.pdf

"A Comparative Study Of Statistical Methods And Machine Learning Approaches For Stock Price Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. ppg156-g161, July-2023, Available at : http://www.jetir.org/papers/JETIR2307623.pdf