{"id":231,"date":"2024-06-03T21:07:35","date_gmt":"2024-06-04T04:07:35","guid":{"rendered":"http:\/\/184.72.63.26\/?p=231"},"modified":"2024-07-02T00:11:49","modified_gmt":"2024-07-02T07:11:49","slug":"stock-price-prediction-using-machine-learning","status":"publish","type":"post","link":"https:\/\/www.wallacel.com\/index.php\/2024\/06\/03\/stock-price-prediction-using-machine-learning\/","title":{"rendered":"Stock Price Prediction using Machine Learning"},"content":{"rendered":"\n

In this project, I will explore using Machine Learning to forecast future stock prices. By leveraging AWS SageMaker Canvas, I’ll build a stock prediction model using time series forecasting and then visualize the results with AWS QuickSight.<\/p>\n\n\n\n

Step1 : Create SageMaker Domain<\/h2>\n\n\n\n

To kick off the project, navigate to the SageMaker console and click on Setup up for single users. This process grants access to SageMaker Canvas by automatically creating a domain and user profile. The domain is essential as it provides a centralized location for storing data models and other resources necessary for this project.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

Step 2: Obtain Historical Data<\/h2>\n\n\n\n

To gather the historical stock data, you can use several sources such as Nasdaq<\/a> and Yahoo Finance<\/a>. While Nasdaq provides data for up to the past 10 years, Yahoo Finance offers a more extensive range, with records dating back to 1986. Therefore, I’ll utilize Yahoo Finance to obtain the comprehensive historical data needed for this project.<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

After downloading the historical data as a CSV file, I’ll make several modifications and save the file as MSFT_20240531.csv<\/code>:<\/p>\n\n\n\n