The trend of stock exchange prices is always uncertain for the stockholders and venture capitalists is there governed by multiple factors that can influence them. In this project we aim to predict the stock market trends using deep learning and machine learning techniques. We had chosen four distinct stock market groups from current stock exchange to be our dataset for experimentation and evaluation. For this purpose, we have taken 10 years of stock data of top IT companies listed on NASDAQ from Yfinance such as Microsoft. This study compares five machine learning models (Decision Tree, Random Forest, Adaptive Boosting (Adaboost), eXtreme Support Vector Classifier (SVC), Logistic Regression and deep learning methods such as Long short-term memory (LSTM). For this purpose, we have taken 10 years of stock data of top IT companies listed on NASDAQ from Yfinance such as Microsoft. This study compares five machine learning models (Decision Tree, Random Forest, Adaptive Boosting (Adaboost), eXtreme Support Vector Classifier (SVC), Logistic Regression and deep learning methods such as Long short-term memory (LSTM). We have initially done the data analysis for these IT companies using past one year data from Yfinance. The evaluatioionn of algorithms and creation of model uses 10 years of stock data from Yfinance. We have truncated the last 60 days of data and used it for testing and prediction.The remaning data of 9 years and 10 months has been used for training the LSTM model. When the predictions are made on the test data which is the last 60 days data and compared with the actual stock values of the last 60 days, we observed that the LSTM model that we have developed has given high accuracy with very minimal deviation. The application is hosted as a web application where the admin of the system can analyze the stock data, compare multiple algorithms on the dataset and create the final model for predicting the stock values. The application is hosted as a web application for users to utilize the services of making future predictions for stock data. The application has been developed to predict the stock values for 4 IT companies but the system is capable of forecasting the stock values for the next 60 days for any given ticker symbol.