• Ashish Premji Nitnaware,
• Dr. Sharvari Govilkar

Finding efficient ways to understand, process, and interpret stock market data into knowledge that can be applied to improved investment decisions is the aim of modern finance. Financial tasks are often very diverse and complicated; they frequently possess unpredictable, dynamic, nonlinear, time-varying, and changeable structural properties; and they are influenced by a wide range of political and economic factors. Researchers and academicians working on the problem of predicting the stock market are divided into two groups: some who think they can create algorithms for this purpose and those who believe the market is efficient and self-corrects when new information emerges. Machine learning methods have created powerful application recently that can mine meaningful data from a sizable database. a lot of study is being done to see the behavior of Machine Learning algorithm over financial time series data like stock market/stock index prices. This work is an attempt to predict and compare stock market trends using machine learning models namely k Nearest Neighbor (KNN), SVM algorithms, Adaboost, and decision trees.

"Investigating Efficiency of Machine learning algorithms over Prediction of Stock Market Indices", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 9, page no.d182-d189, September-2022, Available :http://www.jetir.org/papers/JETIR2209324.pdf

"Investigating Efficiency of Machine learning algorithms over Prediction of Stock Market Indices", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 9, page no. ppd182-d189, September-2022, Available at : http://www.jetir.org/papers/JETIR2209324.pdf