A study on different approaches to the Predictive analysis of stock market Using machine learning

As we move into the future many high technological innovations and analysis formulas are taking place in stock market analysis and transforms into a new era of stock trading. As many cross border open market policies are evolving making the market growth fast and attractive for more investors. That's why many common people and investors are considering stock market as a smart financial investment plan for future. But investing in stocks required many financial analysis and time to eliminate this problem and make stock investment more easy, many researchers and programmers are building many online tools, formulas and analysis patterns. However, adding machine learning algorithms for smart and big analysis is considered to be the most effective and modern approach. This Technique consists of many models that allows to work with non-traditional data, large data based on stocks performance. Advanced ML techniques offers more features like text to data transform, NLP or social media data extraction, sentiment analysis, Gio Political conditions and many more. But Still stock market forecasting and analysis is a complex region as it's a ongoing process consists of large, unstable, incomplete data. This paper explores machine learning-based approaches for stock market prediction through the implementation of a generic framework. Research findings from the few past decades historical data were critically examined, sourced from digital libraries and databases like ACM Digital Library and Scopus. Additionally, we conducted some model's performance test and similarities with other models and their forecasted results.